deliver
Deliver an accepted spec autonomously, from failing acceptance tests to a pull request with green checks.
Skill by taecontrol
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/taecontrol-deliver
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/deliver
What's inside
- Skill name
deliver- Description
- Deliver an accepted spec autonomously, from failing acceptance tests to a pull request with green checks. Use when a spec from `shape` is accepted, or for a bug fix whose reproduction and expected behavior are agreed.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Deliver Take one accepted spec to a pull request the human only has to merge. The spec's examples define success; the acceptance tests make them executable before any production code exists; the rest of the work makes them pass and leaves the code in good shape. Run to the end on your own. ## Start Read the spec at the path you were given, every source its Context and Decisions point to, the project's coding standards, and its gate configuration. Require `Status: Accepted`. For a bug fix, the agreed reproduction and expected behavior are the spec. Work on the current branch in the current worktree. ## 1. Acceptance tests Turn each `test` example into an executable test at the spec's test boundary, with the project's verification method, under the spec's real target conditions. Name each test for the behavior it proves. Run them and watch each go **red** for the right reason: the behavior is missing, not the setup broken. A test for something that must never happen must be able to fail. Commit the tests on their own; when the project's hooks reject failing tests, mark them as expected failures until the code makes them pass. These assertions are the contract. Glue around them, such as setup, selectors, and helpers, may change as the code takes shape. An assertion changes only when it misstates its example; list each such change for the pull request. ## 2. Make it work Make the tests pass, then capture each `capture` example from the running product. Commit as you go. Done when every acceptance test is green, the project's gates pass, and the evidence is captured. What must outlive the spec goes into the change: behavior is already in tests; rationale goes into an ADR through `adr`, and vocabulary and project-wide rules are drafted where `domain-language` and `agents-md` keep them, for the human to accept with the pull request. What only a later issue needs goes into that issue. ## 3. Refine Run `refine` in a fresh context, such as a subagent, with the spec, the diff range from where delivery began, and the assertion changes. When the harness offers no fresh context, run it yourself and say so in the pull request. ## 4. Ship Run `ship` once `refine` finishes. When `refine` stopped on blockers, stop with its report instead. A production change made after `refine` finishes, such as a fix for a CI check or one the human asks for, gets a fresh review of that change and its callers, as `refine`'s later rounds do, before the pull request is ready. ## Decisions along the way Decide reversible choices yourself and record the ones the human would want to know about for the pull request. A one-way door the spec does not settle, such as a migration, a new contract that writes, or a change to a seam an accepted ADR governs, is not one of them. An accepted program design constrains them: follow it where the code agrees, and name each departure from it in the pull request with its reason. Stop and ask when the change needs one, or when evidence shows that an example, a decision in the spec, or an accepted one-way door is wrong, and continue with work that does not depend on it. The examples are the contract, but a number that sets how much to verify, such as a repetition count, a sample size, or a margin, is a decision like any other: before a verification that runs long or repeats, time one run, and when the whole would cost out of proportion to what it adds, that is evidence its decision is wrong. Put anything to the human, a question or a stop such as `refine`'s blockers, so they can answer it without opening the spec: the behavior at stake in plain words, the options, and your recommendation. ## Done The pull request is open, its checks are green, every example is proven by a test or a capture, and every deviation from the spec is named in its description. The human merges.
From taecontrol/skills, MIT.
More from taecontrol/skills
- 0.592score
architect
taecontrol
Settle a one-way door before code locks it: a change to persisted data or its schema, a contract that writes, a security boundary, an ownership model, or a…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
prototype
taecontrol
Make a design question tangible before committing to it: compare production-representative UI directions for a screen, component, or short flow, or drive a…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
strategic-programming
taecontrol
Apply strategic programming to non-trivial implementation and repair work when green tests alone cannot establish a maintainable design.
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
refine
taecontrol
Review a working change with fresh eyes against its spec, then make it right and make it fast without changing the behavior its acceptance tests lock, in at…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
research
taecontrol
Investigate a bounded question against high-trust primary sources through parallel independent research, then produce a cross-checked Markdown report.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
setup-verification
taecontrol
Give agents hands and eyes on a project: one way to launch, drive, and observe the real product, and acceptance tests that run fast and the same locally and…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
spike
taecontrol
Run a bounded technical experiment when observation is needed to settle feasibility, integration, performance, or tool behavior.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
ship
taecontrol
Publish finished work as a pull request and drive its CI checks to green.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
diagnosing-bugs
taecontrol
Establish the mechanism behind a hard, intermittent, recurring, or performance failure from a faithful reproduction or distinguishing runtime evidence.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
garden
taecontrol
Tend a codebase between features: find drift in one area, group it by cause, and fix the causes worth their cost in one behavior-preserving pull request.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
shape
taecontrol
Shape a problem with the human into one accepted spec: what to build, what success means, and how to prove it, before anyone writes production code.
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
skill-guide
taecontrol
Explain available skills, compare their boundaries, or recommend what the user should invoke next.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/taecontrol/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from taecontrol
- 0.592score
strategic-programming
taecontrol
Apply strategic programming to non-trivial implementation and repair work when green tests alone cannot establish a maintainable design.
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
prototype
taecontrol
Make a design question tangible before committing to it: compare production-representative UI directions for a screen, component, or short flow, or drive a…
SkillAFreshness: A★ 1Claude Code +9 - 0.592score
architect
taecontrol
Settle a one-way door before code locks it: a change to persisted data or its schema, a contract that writes, a security boundary, an ownership model, or a…
SkillAFreshness: A★ 1Claude Code +9 - 0.589score
refine
taecontrol
Review a working change with fresh eyes against its spec, then make it right and make it fast without changing the behavior its acceptance tests lock, in at…
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
diagnosing-bugs
taecontrol
Establish the mechanism behind a hard, intermittent, recurring, or performance failure from a faithful reproduction or distinguishing runtime evidence.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
garden
taecontrol
Tend a codebase between features: find drift in one area, group it by cause, and fix the causes worth their cost in one behavior-preserving pull request.
SkillAFreshness: A★ 1Claude Code +9
Cite this page
deliver skill. Agent Mart. https://agentmart.dev/skills/taecontrol-deliver (last updated 2026-10-24)