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

implement

Skill1 starsChanged 13 days agoMITView on GitHub

Execute the tasks defined in tasks.md sequentially by user story, respecting dependencies and parallelism markers, updating task progress, and grounding changes in codebase OKF docs. Use when implementing tasks with /implement.

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, ask-matt 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.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • GoogleSkill

    ask-matt

    Ask which skill or flow fits your situation. A router over the skills in this repo.

    Also in 91 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 50 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 88 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 42 projects that use this

  • GoogleSkill

    to-spec

    Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 168 projects that use this

  • +3 more from google

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify prerequisites: Run buddhi sdd check --require-tasks --include-tasks --json via the terminal-runner agent.

    line 21
  2. Very specific:

    Read tasks.md for the execution plan and task IDs.

    line 26
  3. Very specific:

    Read plan.md for architectural context, project structure, and file targets.

    line 27
  4. Very specific:

    Read spec.md for user stories and acceptance criteria.

    line 28
  5. Very specific:

    Phase 1: Setup: Run project/tooling setup commands via terminal-runner (or buddhi scripts rtk run --) to keep context lean.

    line 34
  6. Very specific:

    Run /refactor-clean to ensure no temporary shims or dead wrappers linger.

    line 44
  7. Very specific:

    If decisions were made where the spec was silent, record them in .buddhi/specs/<branch>/choices.md (following the /audit-choices format: …

    line 45
  8. Very specific:

    After completing each task, edit tasks.md to mark the task completed (- [x] TXXX).

    line 51

“Common” is measured: kept by at least 6 in 10 of the 171 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

/implement

$ARGUMENTS

Implementation phase in the Spec-Driven Development (SDD) lifecycle. Executes tasks from .buddhi/specs/<branch>/spec-tasks.md in phased order, prioritizing user stories from MVP (P1) onwards and keeping tasks.md progress up to date.

Steps

  1. Verify prerequisites: Run buddhi sdd check --require-tasks --include-tasks --json via the terminal-runner agent. This strictly ensures that spec.md, plan.md, and tasks.md all exist before proceeding. If any are missing, stop immediately and guide the user to run the missing skill (/specify, /spec-plan, or /spec-tasks).
  2. Load context:
    • Read tasks.md for the execution plan and task IDs.
    • Read plan.md for architectural context, project structure, and file targets.
    • Read spec.md for user stories and acceptance criteria.
    • Consult .buddhi/docs/ and query the code graph via Buddhi MCP tools (buddhi_search, buddhi_read, see the okf-context skill) for modules being modified. If OKF docs are absent, proceed directly with existing source files.
  3. Phased execution: Execute tasks phase by phase:
    • Phase 1: Setup: Run project/tooling setup commands via terminal-runner (or buddhi scripts rtk run --) to keep context lean.
    • Phase 2: Foundational: Implement core blocking items (schemas, models, base routes, configs). Checkpoint: Verify foundation builds cleanly before proceeding to user stories.
    • Phase 3+: User Story N (P1 MVP → P2 → P3...):
      • Implement story tasks in order (tests first if specified, then models, services, endpoints/UI).
      • Dispatch domain specialists (backend, frontend, database, etc.) for complex domain work.
      • For UI/frontend implementation: obey .agents/rules/a11y.md at all times. Use native HTML elements over ARIA recreation. For non-derivable pattern choices between equally conformant alternatives, record in A11Y-DECISIONS.md. Run buddhi scripts verify-a11y and buddhi scripts contrast after implementing frontend components.
      • For tasks marked [P], parallel implementation across distinct files is permitted.
      • Checkpoint: After finishing each story, test it independently to confirm working state.
      • Maintenance & Choices Checkpoint:
        • Run /refactor-clean to ensure no temporary shims or dead wrappers linger.
        • If decisions were made where the spec was silent, record them in .buddhi/specs/<branch>/choices.md (following the /audit-choices format: sound, unsound, needs-user).
    • Phase N: Polish: Documentation, linting, formatting, cleanup, and A11Y static gate verification.
    • Handoff Support: If the implementation must pause or move to another agent/session mid-flight, run /handoff-spec to record active context directly into the spec folder.
  4. Update task progress: After completing each task, edit tasks.md to mark the task completed (- [x] TXXX).
  5. Next step: Once all tasks in tasks.md are completed, inform the user and suggest running /verify to execute full acceptance verification against the specification.

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