implement
Implement a piece of work described by a spec or set of tasks.
Skill by nathanstaines
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nathanstaines-implement
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/implement
What's inside
- Skill name
implement- Description
- Implement a piece of work described by a spec or set of tasks.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
Implement the work described by the user in the spec or tasks. The task tracker conventions live in `docs/agents/task-tracker.md`. If that file doesn't exist, tell the user to run `/setup-skills`. ## Steps 1. **Fetch the work.** From the tracker, fetch the referenced task per the conventions and check its blocking edges. An open blocker ends the session: say so, and offer an unblocked task instead while no work has started. The blocked task gets its own session later. Read the parent spec, or a `spec.md` sitting beside the task in the feature directory, before starting so the implementation decisions and agreed seams carry over. 2. **Mark it in-progress** per the tracker conventions, replacing `ready` when the work is a taskless spec. Already in-progress means a session probably died mid-flight: say when it was last touched, then ask whether to continue from where it stands or reset it to its unstarted state and start clean. Picking one up blind is how half-finished work gets built on twice. 3. **Build it.** Use the project's domain glossary vocabulary and respect any ADRs in the area you're touching (see `docs/agents/domain.md`). The `### Testing` stance in the Agent skills block decides how: where tests are welcome, call the Skill tool with "tdd" and test at pre-agreed seams, running single test files regularly and the full suite once at the end; where the project is test-free, verify by hand, per the spec's Verification section when one exists. Run the typechecker regularly when the project has one. 4. **Tick each acceptance criterion as you meet it** rather than all of them at the end, so a session that doesn't finish still leaves an accurate picture of how far it got. 5. **Close the task** per the tracker conventions, clearing its in-progress status as part of closing it, only when every acceptance criterion is met and ticked and with any deviation from the task description noted. Then stop, and say the changes are unreviewed. Reviewing is the user's call from a fresh session, `/code-review` against the state you started from; leave it for them to invoke and do nothing further until they ask. Implement only the referenced task: when it's done, stop rather than pulling the next frontier task into the same session. A fresh session can run `/progress` to pick the next frontier task up. Only record the work in version control (commit, check in, push) when explicitly asked. Applying requested changes never implies recording them, even if that was discussed beforehand.
From nathanstaines/skills, MIT.
More from nathanstaines/skills
- 0.565score
tdd
nathanstaines
Test-driven development, the red → green loop.
SkillAFreshness: AClaude Code +9 - 0.565score
code-review
nathanstaines
Two-axis review of the changes since a fixed point, Standards and Spec.
SkillAFreshness: AClaude Code +9 - 0.561score
architecture-review
nathanstaines
Scan a codebase, or a named area of it, for deepening opportunities, present them as a visual HTML report, then triage every candidate yes/maybe-later/no and…
SkillAFreshness: AClaude Code +9 - 0.561score
scout
nathanstaines
Chart a large, foggy piece of work as a map of decision tasks on the project's task tracker, then resolve them one at a time until the way to a spec is clear.
SkillAFreshness: AClaude Code +9 - 0.561score
progress
nathanstaines
Show the state of every feature in the task tracker at a glance: what's done, what's in flight, what's startable now and which specs are still waiting on a…
SkillAFreshness: AClaude Code +9 - 0.561score
setup-skills
nathanstaines
Configure this project for engineering skills.
SkillAFreshness: AClaude Code +9 - 0.561score
to-tasks
nathanstaines
Break a plan, spec or the current conversation into a set of tracer-bullet tasks, each declaring its blocking edges, published to the configured task tracker.
SkillAFreshness: AClaude Code +9 - 0.558score
retro
nathanstaines
Review a coding session and propose improvements to the agent's environment for future runs.
SkillAFreshness: AClaude Code +9 - 0.544score
diagnose-bugs
nathanstaines
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: AClaude Code +9 - 0.539score
domain-modelling
nathanstaines
Build and sharpen a project's domain model.
SkillAFreshness: AClaude Code +9 - 0.539score
prototype
nathanstaines
Build a throwaway prototype to answer a design question.
SkillAFreshness: AClaude Code +9 - 0.539score
codebase-design
nathanstaines
Shared vocabulary for designing deep modules.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 6, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/nathanstaines/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from nathanstaines
- 0.565score
tdd
nathanstaines
Test-driven development, the red → green loop.
SkillAFreshness: AClaude Code +9 - 0.565score
code-review
nathanstaines
Two-axis review of the changes since a fixed point, Standards and Spec.
SkillAFreshness: AClaude Code +9 - 0.561score
to-tasks
nathanstaines
Break a plan, spec or the current conversation into a set of tracer-bullet tasks, each declaring its blocking edges, published to the configured task tracker.
SkillAFreshness: AClaude Code +9 - 0.561score
progress
nathanstaines
Show the state of every feature in the task tracker at a glance: what's done, what's in flight, what's startable now and which specs are still waiting on a…
SkillAFreshness: AClaude Code +9 - 0.561score
architecture-review
nathanstaines
Scan a codebase, or a named area of it, for deepening opportunities, present them as a visual HTML report, then triage every candidate yes/maybe-later/no and…
SkillAFreshness: AClaude Code +9 - 0.561score
scout
nathanstaines
Chart a large, foggy piece of work as a map of decision tasks on the project's task tracker, then resolve them one at a time until the way to a spec is clear.
SkillAFreshness: AClaude Code +9
Cite this page
implement skill. Agent Mart. https://agentmart.dev/skills/nathanstaines-implement (last updated 2026-10-24)