agentleFS
Sign inStart free
websublimewebsublime/mister-anderson/skills/spec/SKILL.md

spec

Skill3 starsChanged 7 months agoMITView on GitHub

Create a detailed technical spec grounded in validated research. Dispatches Ada with PRD + Plan + Research as inputs. Only after plan and research exist.

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, ios-clean and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 7 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 6 projects that use this

  • +2 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 5 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a detailed technical specification from an approved plan, validated by research.

    line 9
  2. Distinctive:

    If the user provides $ARGUMENTS, analyze them for:

    line 14
  3. Very specific:

    Plan must exist and be APPROVED: Ask the user for the plan path (e.g., docs/plans/02-plan-mcp-complete.md).

    line 21
  4. Very specific:

    PRD must exist: Ask the user for the PRD path (e.g., docs/PRD.md).

    line 23
  5. Very specific:

    No plan found. Recommend running /plan first.

    line 27
  6. Very specific:

    Ask: "Do you want to run /research first, or proceed without research?"

    line 33
  7. Very specific:

    If user wants research → stop and recommend /research

    line 34
  8. Distinctive:

    If user proceeds → include this warning in the dispatch prompt </on-check-fail>

    line 35
  9. Very specific:

    No PRD found. Recommend running /requirements first.

    line 39
  10. Distinctive:

    If research docs found, read them and list for the user

    line 44
  11. Very specific:

    Ensure the docs/specs/ directory exists (create if needed)

    line 49
  12. Distinctive:

    Verify the spec file was created at the agreed path

    line 64

“Common” is measured: kept by at least 6 in 10 of the 145 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

Spec

Create a detailed technical specification from an approved plan, validated by research.

<on-init> If the user provides $ARGUMENTS, analyze them for: - A plan path - A PRD path - Specific focus areas or constraints </on-init><on-check> 1. **Plan must exist and be APPROVED.** Ask the user for the plan path (e.g., `docs/plans/02-plan-mcp-complete.md`). Read to confirm. 2. **Research docs should exist.** Determine the phase number from the plan filename (e.g., `02`). Search for `docs/research/{NN}-research-*.md`. 3. **PRD must exist.** Ask the user for the PRD path (e.g., `docs/PRD.md`). Read to confirm. </on-check><on-check-fail if="plan"> No plan found. Recommend running `/plan` first. </on-check-fail><on-check-fail if="research"> Warn: "No research docs found for this phase. The spec will be based on unvalidated assumptions from the plan. This historically causes drift during implementation."

Ask: "Do you want to run /research first, or proceed without research?"

  • If user wants research → stop and recommend /research
  • If user proceeds → include this warning in the dispatch prompt</on-check-fail>
<on-check-fail if="prd"> No PRD found. Recommend running `/requirements` first. </on-check-fail><on-execute> 1. **List research findings:** - If research docs found, read them and list for the user - Confirm which docs to include in the dispatch
  1. Define output location:
    • Suggest default: docs/specs/{NN}-spec-{feature-kebab}.md
    • Ensure the docs/specs/ directory exists (create if needed)

  2. Dispatch using exactly these parameters — no more, no less:

    Agent(
    subagent_type="architect",
    prompt="Create a detailed TECHNICAL SPEC for the plan at {plan_path}. PRD for context: {prd_path}. Research findings (MUST READ before designing): {research_paths_comma_separated}. The research docs contain validated assumptions — your design MUST align with the confirmed findings and address any contradictions or risks identified. Do NOT re-assume what research already validated or contradicted. If research contradicted a plan assumption, design the spec around the reality documented in the research, not the original plan assumption. Save to {spec_path} with status DRAFT. Iterate with the user until APPROVED."
)

    Do NOT add extra parameters unless the user explicitly requests it.

    </on-execute>
<on-complete> 1. Verify the spec file was created at the agreed path 2. Show the user the status from Ada's report (DRAFT or APPROVED) </on-complete><on-complete if="status=DRAFT"> Inform the user they can continue iterating with Ada. </on-complete><on-next> Recommend proceeding with `/tasks` to decompose the spec into trackable issues. </on-next>

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