author-pragma-dsl

REVIEW · 68
Registry indexed

Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation resources. Use when a user asks Pragma to create, change, configure, test, evaluate, or repair an Expert, team, Flow, Run Dry suite, schedule, trigger, or Automation in the current Pragma p

Verified installs0
Stars106
Version1.0.0
Quality66/100 · Promising
Trust68/100 · Sandbox only
Audit79/100 · Needs review

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

Research agents

I need my agent to research a topic, compare sources, and produce a concise report.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add pqpo/pragma --skill author-pragma-dsl

Maintenance

fresh

Pushed today

Risk

Needs review

Financial research output is not financial advice; require human review before any live investment decision

GitHub quality

106

66/100 Quality · 76/100 Trust

Coverage tags

ResearchResearch agentsagent-skill

Review notes

Financial research output is not financial advice; require human review before any live investment decision · Repository license is NOASSERTION, unclear licensing.

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
66

Useful candidate, but compare it with alternatives before adopting.

Trust

Sandbox only
68

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
79

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

106 GitHub stars

Repo activity

106 stars, 10 forks

Maintenance

Pushed today

License

NOASSERTION

Install

npx skills add pqpo/pragma --skill author-pragma-dsl

Install safety

standard package or runtime install path

Permission surface

filesystem or document access, database access

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Repository license is NOASSERTION, unclear licensing.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Stars/forks activity: 106 stars, 10 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add pqpo/pragma --skill author-pragma-dsl
Policy
review
Human review
yes

Trust and risk

Trust
68/100
Audit
79/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add pqpo/pragma --skill author-pragma-dsl

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Repository license is NOASSERTION, unclear licensing.
  • No OpenAgentSkill engagement data yet
  • Financial research output is not financial advice; require human review before any live investment decision

Agent safety v2

59/100 · Review before install

Reviewed with permission notesreview

Usable candidate, but the agent should surface permission and audit notes before installation.

Require human approval before installing into a real workspace.

Resolve via API

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

medium

Database access

Skill may inspect schemas, query databases, or work with persistent stores.

  • Financial research output is not financial advice; require human review before any live investment decision

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pqpo-author-pragma-dsl

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use author-pragma-dsl in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20author-pragma-dsl%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/pqpo-author-pragma-dsl/install
Install command: npx skills add pqpo/pragma --skill author-pragma-dsl
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use author-pragma-dsl for this task. Review https://www.openagentskill.com/api/skills/pqpo-author-pragma-dsl/install, then install with: npx skills add pqpo/pragma --skill author-pragma-dsl

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

65/100

Research agents

Platforms

Claude Code

Audit report

Needs review · 79/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

65
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Research agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 66/100 quality profile

review first

  • Repository license is NOASSERTION, unclear licensing.
  • No OpenAgentSkill engagement data yet

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

68
OpenAgentSkill Trust Score

GitHub adoption

INFO

106 GitHub stars

Stars/forks activity

CHECK

106 stars, 10 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

Pushed today

License clarity

PASS

NOASSERTION

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Repository license is NOASSERTION, unclear licensing.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Stars/forks activity: 106 stars, 10 forks; issue activity unavailable in current metadata
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

66
GitHub stars
106
Freshness
Today
Install ready
Yes
License
NOASSERTION
Review before install: Repository license is NOASSERTION, unclear licensing.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: author-pragma-dsl description: Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation resources. Use when a user asks Pragma to create, change, configure, test, evaluate, or repair an Expert, team, Flow, Run Dry suite, schedule, trigger, or Automation in the current Pragma project. ---

# Author Pragma DSL

Translate the user's intent into the smallest complete DSL change. Treat the interpreter as the source of truth and use only the Pragma DSL tools to inspect, validate, and save resources.

## Workflow

1. Discuss missing intent before changing definitions. 2. Call `list_dsl_resources`, then read every project resource that will be changed or referenced. Before creating an ExpertTeam, read every existing coordinator or member and include any new ones in the same change-set. A Host Runtime or Capability option that is not yet a project resource cannot be read and is the only exception. 3. Before creating or changing an Expert, call `list_expert_options`. Confirm a listed Runtime model, recommend only listed capabilities that match the user's intent, and select only a listed avatar persona. When the user has not specified an avatar, either recommend the persona whose traits best match the Expert's role or present a concise choice of relevant personas. Preserve an existing avatar when editing unless the user asks to change it. Ask whether to use the recommendation, customize it, or enable no capabilities. Reuse an existing project RuntimeProfile when its Runtime, provider, model, and thinking level match the selection; otherwise use the option's `runtimeProfileRef`. Never author a duplicate RuntimeProfile. 4. Read the relevant reference file below before drafting YAML. 5. Before authoring a new resource, allocate only the IDs needed for the user's current confirmed request. Use the returned Host-generated IDs and exact references. Preserve IDs when editing; never invent, copy, or change an ID. 6. For a new or non-trivial Flow change, create a Flow draft and build it in small batches with `update_flow_draft`: contracts, steps, start, transitions, and loops. Read diagnostics after every batch. Pass `operations` as a native JSON array, never as a string containing serialized JSON; string parsing is only a recovery path. The update response is a compact revision summary. Call `get_flow_draft` only when the complete current resource is needed. Flow drafts never contain Run Dry cases and never require an Evaluation draft. 7. Call `validate_flow_draft`, then `prepare_flow_draft` when the Flow is structurally complete. `prepare_flow_draft` prepares the Flow and optional non-Evaluation dependencies only. Fix every diagnostic, explain the normalized diff, and call `commit_dsl_changes` with the returned change-set ID. Do not create, prepare, or commit an Evaluation in this Flow transaction. 8. After the Flow commit succeeds, ask whether the user wants to create a test set and run it. The user may skip. If they skip, report the committed Flow and stop. Do not allocate an Evaluation ID or create an Evaluation draft before the user confirms, unless their original request already explicitly asked for the test set. 9. When the user confirms, or when they ask to test an existing committed Flow, read [references/run-dry.md](references/run-dry.md). Target the exact committed Flow ref. By default, generate and upsert exactly one case, immediately run that case, and fix it until it passes before creating another. Use cumulative `coverage.missing` as the next-case backlog. Only use batches when the user explicitly requests them; update, read, or run 2–10 cases per call, and fix every failure in the current batch before adding more. Never emit or pass a complete Evaluation YAML document. 10. Save the test set independently: call `prepare_evaluation_draft` with its exact draft revision, then pass the returned `changeSetId` to `commit_dsl_changes`. This commit changes only the Evaluation; it is never part of `prepare_flow_draft` or `additionalSources`. Use `prepare_dsl_changes` directly only for complete non-Flow resources. Its `sources` input is always an array with one complete YAML document per item, even for one resource. 11. Fix every diagnostic. Never bypass validation or hand-edit project files. If the project revision changed, reread affected resources and explicitly rebase the draft before retrying. 12. After each commit tool returns, always report success or failure, the committed project revision, and the changed canonical refs.

Before preparing, verify that every new ID came from `allocate_dsl_resource_ids`, every Evaluation targets an exact Flow ref, every project ref was read, every ContextStore mount declares `ref`, `namespace`, and `required`, and no existing RuntimeProfile, Capability, or ContextStore is repeated in `sources`. Follow diagnostic `source` and `path` values literally; never invent a field derivation rule to work around validation.

For Automation work, use `list_automations` before editing. Use `save_automation` instead of the generic prepare/commit pair because the host workspace and permission binding must be saved with the portable DSL. Use the same tool to enable or disable an Automation. `delete_automation` retains existing Missions; `reset_automation_session` only changes which Mission the next event continues. Before preparing or saving, enforce the Automation metadata and prompt limits documented in `references/automation.md`; never rely on the host to truncate authored values.

## References

- Expert resources: read [references/expert.md](references/expert.md). - Expert avatar personas: read [references/avatars.md](references/avatars.md) before selecting or changing an Expert avatar. - ExpertTeam resources: read [references/expert-team.md](references/expert-team.md). - Flow resources: read [references/flow.md](references/flow.md). - Flow run dry cases: read [references/run-dry.md](references/run-dry.md). - Automation resources: read [references/automation.md](references/automation.md). - Tested Flow patterns: read [references/flow-patterns.md](references/flow-patterns.md). - Exact refs, shared resources, and versioning: read [references/resources-and-references.md](references/resources-and-references.md).

Do not invent fields from memory. If validation disagrees with a reference example, follow the diagnostic and the current interpreter schema.

Technical details

Version
1.0.0
License
NOASSERTION
Last updated
Aug 24, 2026
Published
Aug 24, 2026

Decision snapshot

Fallback candidate

65
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

79
Needs review
Security
81/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for author-pragma-dsl, ready for a manual X post.

Curator note
author-pragma-dsl: Create and update validated pragma/v5 Expert, ExpertTeam, Flow, Evaluation, and Automation re...

106 stars

https://www.openagentskill.com/skills/pqpo-author-pragma-dsl?ref=x
Open X draft
Optional reply with install command
Listing + install path for author-pragma-dsl:
https://www.openagentskill.com/skills/pqpo-author-pragma-dsl?ref=x

Install: npx skills add pqpo/pragma --skill author-pragma-dsl

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
pqpo
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to pqpo but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/pqpo-author-pragma-dsl?metric=listed&label=Listed)](https://www.openagentskill.com/skills/pqpo-author-pragma-dsl)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/pqpo-author-pragma-dsl?metric=trust&label=Trust)](https://www.openagentskill.com/skills/pqpo-author-pragma-dsl)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/pqpo-author-pragma-dsl?metric=audit&label=Audit)](https://www.openagentskill.com/skills/pqpo-author-pragma-dsl/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/pqpo-author-pragma-dsl?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/pqpo-author-pragma-dsl)

Author

P

pqpo

@pqpo

Platform fit

Health signals

GitHub stars
106
Quality score
37/100
Last GitHub push
Aug 24, 2026
Framework hints
Unknown
OpenAgentSkill views
0
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

68
  • GitHub adoption106 GitHub starsINFO
  • Stars/forks activity106 stars, 10 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenancePushed todayPASS
  • License clarityNOASSERTIONPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskno major dependency risk hints in public metadataPASS