agentleFS
nelantonenelantone/cognivia/.agents/skills/task-brief/SKILL.md

task-brief

Skill1 starsChanged 2 months agoMITView on GitHub

Turn an implementation, debugging, audit, or migration request into a precise scope, objective, constraint, file, validation, and reporting brief before work begins. Use for multi-file, ambiguous, architectural, or staged work and explicit requests for a task brief. Do not use for architecture inventory, refactor execution, commit review, session handoffs, or trivial requests with complete acceptance criteria.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when a request needs scope clarification, acceptance criteria, protected areas, phased work, or a validation contract before …

    line 15
  2. Distinctive:

    Do not use for a full architecture inventory, behavior-preserving extraction, documentation editing, commit preparation, or handoff …

    line 20
  3. Distinctive:

    Stop with the brief; do not implement it.

    line 44
  4. Distinctive:

    Do not infer permission for product edits, provider calls, dependencies, Git mutations, or broader cleanup.

    line 56
  5. Distinctive:

    Do not turn an uncertain dependency assumption into an architecture finding.

    line 58
  6. Distinctive:

    Do not include secrets or credential values.

    line 59
  7. Distinctive:

    Verify named existing paths before presenting them as current.

    line 63
  8. Distinctive:

    Check that acceptance criteria cover the objective and that non-goals prevent scope drift.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Task Brief

Purpose

Produce an implementation-ready contract without solving or implementing the task. Separate verified repository facts from assumptions and decisions.

Trigger

Use when a request needs scope clarification, acceptance criteria, protected areas, phased work, or a validation contract before implementation.

Do not trigger

Do not use for a full architecture inventory, behavior-preserving extraction, documentation editing, commit preparation, or handoff generation. Route those responsibilities to their dedicated skills.

Inputs

  • User objective and acceptance criteria.
  • Current branch, working-tree state, and relevant repository instructions.
  • Known implementation evidence and unresolved assumptions.
  • Allowed and protected product areas, files, dependencies, and provider use.
  • Required final report or artifact format.

Workflow

  1. Inspect only enough repository context to define the task accurately.
  2. Record observed facts separately from assumptions and open decisions.
  3. State one concrete objective and measurable acceptance criteria.
  4. Mark affected areas and explicitly unchanged areas: frontend, backend, prompts, graph, RAG, memory, persistence, providers, tests, dependencies, configuration, and deployment.
  5. List expected files, protected files, constraints, and non-goals.
  6. Identify validation appropriate to the proposed scope using AGENTS.md.
  7. Define the required final report, approval boundary, risks, and rollback point.
  8. Stop with the brief; do not implement it.

Outputs

Return a concise brief using the task brief format. Call out any missing decision that genuinely blocks safe implementation.

Safety

  • Remain read-only unless the user separately authorizes writing the brief to a named path.
  • Do not infer permission for product edits, provider calls, dependencies, Git mutations, or broader cleanup.
  • Do not turn an uncertain dependency assumption into an architecture finding.
  • Do not include secrets or credential values.

Validation

  • Verify named existing paths before presenting them as current.
  • Label planned paths and commands as planned.
  • Check that acceptance criteria cover the objective and that non-goals prevent scope drift.
  • Confirm that the validation plan and final report match the requested scope.

References

  • AGENTS.md — durable repository rules and validation.
  • docs/agents/README.md — tooling ownership.
  • Task brief format — output structure.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.