agentleFS
Sign inStart free
browozbrowoz/agentic-sdlc-skills/skills/agentic-spec/SKILL.md

agentic-spec

Skill4 starsChanged 5 months agoMITView on GitHub

Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create AGENTS.md. Do NOT use for small bug fixes, simple edits, one-off scripts, direct implementation requests, or explanation-only questions.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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 this skill to convert intent into a compact engineering contract before implementation.

    line 14
  2. Distinctive:

    If requirements are materially ambiguous, ask only the blocking question.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Agentic Spec

Use this skill to convert intent into a compact engineering contract before implementation. Keep the result proportional; do not create ceremony for work that only needs a direct fix.

Workflow

  1. Classify rigor:
    • prototype: throwaway exploration, personal tool, or demo.
    • internal: team feature, workflow automation, or shared tool.
    • production: user-facing, security-sensitive, data-sensitive, or agentic system with tools/actions.
  2. Gather the six context types:
    • Instructions: roles, constraints, repo rules, user priorities.
    • Knowledge: APIs, schemas, business rules, source docs.
    • Memory: relevant project state and previous decisions.
    • Examples: existing patterns, input/output examples, nearby code.
    • Tools: required APIs, MCP servers, CLIs, sandboxes, permissions.
    • Guardrails: explicit boundaries, non-goals, unsafe actions.
  3. Generate SPEC.md from assets/templates/SPEC.md.
  4. For AGENTS.md work, apply the filter test: omit anything discoverable from the codebase, keep project-level rules under 200 lines, and push scoped rules into subdirectories.
  5. If requirements are materially ambiguous, ask only the blocking question. Otherwise record assumptions in the spec and continue.

Rigor Scaling

  • Prototype: one-page spec, 1-2 edge cases, manual verification acceptable.
  • Internal: focused spec, at least 3 edge cases, automated test plan expected.
  • Production: full six-context spec, threat/data boundaries, measurable success criteria, eval/security/deploy follow-up links.

References

Read ../agentic-engineering-sdlc/references/day1_sdlc_and_context.md only when deeper context-engineering or AGENTS.md guidance is needed.

Done Criteria

  • SPEC.md has goal, context, constraints, edge cases, out of scope, and success criteria.
  • Rigor level is explicit and justified.
  • Assumptions and user decisions are separated.
  • Next recommended skill is named only when useful: agentic-evals, agentic-security-review, or agentic-production-readiness.

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.

Check your setup, free