agentleFS
Sign inStart free
BuddhiliveBuddhilive/buddhi-cli/.agents/skills/specify/SKILL.md

specify

Skill1 starsChanged 13 days agoMITView on GitHub

Initialize and refine a feature specification in the Spec-Driven Development (SDD) lifecycle by creating a feature branch, scaffolding spec.md from the template, grounding requirements in codebase OKF docs, and defining prioritized, independently testable user stories. Use when starting a new feature specification with /specify.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use discovery, discover and 8 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.
  • robzolkosSkill

    discovery

    Quick user-centric interview to capture requirements from a time-poor stakeholder.

    Also in 3 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 4 projects that use this

  • MicrosoftSkill

    spec-review

    Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.

    Also in 3 projects that use this

  • MicrosoftSkill

    init

    Also in 5 projects that use this

  • MetaSkill

    roadmap

    Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

    Also in 3 projects that use this

  • sahinSkill

    execute

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 2 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    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. Very specific:

    Start the Spec-Driven Development (SDD) cycle for a new feature request.

    line 15
  2. Very specific:

    If the task has major unknowns or design ambiguity, suggest running /explore-unknowns to complete a 4-quadrant unknown walk (known knowns, …

    line 22
  3. Very specific:

    If the feature depends on empirical heuristics, rankings, or algorithm tuning, suggest running /auto-research to produce a parameter-effect …

    line 23
  4. Very specific:

    Update code graph: Run buddhi generate via the terminal-runner agent to ensure the code graph (.buddhi/graphs/tree-graph.db and …

    line 24
  5. Very specific:

    Scaffold feature: Run buddhi sdd create $ARGUMENTS --json via the terminal-runner agent.

    line 27
  6. Distinctive:

    Clarify requirements: Ask clarifying questions one at a time — purpose, target users, constraints, and scope boundaries.

    line 35
  7. Very specific:

    Ensure P1 represents a standalone, viable MVP slice.

    line 41
  8. Distinctive:

    If the feature involves UI, web surfaces, or interactive frontend components, verify against DESIGN.md design tokens (or suggest …

    line 47
  9. Very specific:

    Write specification: Write the refined specification to the SPEC_FILE path (.buddhi/specs/<branch>/spec.md).

    line 50

“Common” is measured: kept by at least 6 in 10 of the 27 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

/specify

$ARGUMENTS

Start the Spec-Driven Development (SDD) cycle for a new feature request. Scaffolds a structured spec.md under .buddhi/specs/<branch>/ and refines it interactively with prioritized, independently testable user stories. No code writing in this skill.

Steps

  1. Pre-spec discovery (when needed):
    • If the task has major unknowns or design ambiguity, suggest running /explore-unknowns to complete a 4-quadrant unknown walk (known knowns, known unknowns, unknown knowns, unknown unknowns) before codifying the spec.
    • If the feature depends on empirical heuristics, rankings, or algorithm tuning, suggest running /auto-research to produce a parameter-effect map and verified incumbent in .buddhi/specs/<branch>/research.md.
  2. Update code graph: Run buddhi generate via the terminal-runner agent to ensure the code graph (.buddhi/graphs/tree-graph.db and tree-graph.json) is up to date before inspecting or scaffolding.
  3. Scaffold feature: Run buddhi sdd create $ARGUMENTS --json via the terminal-runner agent. This computes the feature number, branch name, creates .buddhi/specs/<branch>/, and initializes spec.md from the spec template. Parse the returned JSON to obtain BRANCH_NAME and SPEC_FILE.
  4. Codebase grounding: Consult .buddhi/docs/index.md and use Buddhi MCP tools (buddhi_search, buddhi_read, see the okf-context skill) or query .buddhi/graphs/tree-graph.db / tree-graph.json for any subsystems the request touches. If OKF docs are missing or not generated yet, proceed gracefully without failing.
  5. Clarify requirements: Ask clarifying questions one at a time — purpose, target users, constraints, and scope boundaries. Propose concrete answers grounded in what step 3's docs found so the user can confirm with minimal friction. Stop and wait for the user's answer between questions; do not batch them.
  6. Define user stories & priorities:
    • Organize functionality into prioritized user stories (P1, P2, P3...).
    • Ensure P1 represents a standalone, viable MVP slice.
    • For each story, provide plain-language journey, priority rationale, independent test description, and concrete Given / When / Then acceptance scenarios.
  7. Detail requirements & success criteria:
    • List functional requirements (FR-001, FR-002...). Mark any ambiguities with [NEEDS CLARIFICATION].
    • List key entities if data/state is involved.
    • If the feature involves UI, web surfaces, or interactive frontend components, verify against DESIGN.md design tokens (or suggest /design-md) and include an explicit Accessibility (A11Y) requirement (WCAG 2.2 AA / EN 301 549, keyboard operability, contrast compliance, and screen-reader semantics) referencing the a11y skill.
    • Define measurable, technology-agnostic success criteria (SC-001...).
    • Capture edge cases and boundary conditions.
  8. Write specification: Write the refined specification to the SPEC_FILE path (.buddhi/specs/<branch>/spec.md).
  9. Next step: Present the completed spec.md summary to the user and prompt them to run /spec-plan to proceed to the architecture and implementation planning phase.

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