CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

build-it

Builds a change end to end, from the issue to a reviewed draft PR. Implement, review, hunt invariants, QA in real projects, open the PR, act on the bot reviews, then hand over to a human.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplarily lean orchestrator skill: a nine-step pipeline with explicit done conditions, validation loops, held-decision rules, and load-on-demand references to the sub-skills that do each step's work. The only minor weakness is a few actionability gaps where specifics (focused tests, Greptile review mechanics) are deferred to external documents.

DimensionReasoningScore

Conciseness

The ~46-line body is lean and assumes competence: no concept explanations, no padding, and every clause carries non-obvious project-specific information (e.g., "a subagent cannot read this conversation", "origin/next moves during a session", "The reviews compare commits, so they do not see uncommitted work"). It matches the anchor where every token earns its place.

5 / 5

Actionability

Guidance is mostly executable: exact commands (`cd code && yarn fmt:write`), concrete branch instruction ("Branch from `origin/next` and record the base SHA"), copy-paste-ready PR body formats (`Closes #<number>`, `Closes [SB-<number>](<Linear URL>)`), and explicit per-step done conditions. Minor gaps keep it below a 5 — "Run the focused tests" never says which tests, and mechanics like "Ask Greptile for a review, as [Pull requests] says" are deferred to external docs rather than given inline.

4 / 5

Workflow Clarity

Nine clearly sequenced steps, each with an explicit done condition ("Done when the focused tests pass and the working tree is clean"; "Done when the only unresolved bot threads are the high-severity findings you disagree with") and built-in validation feedback loops ("run it again until only findings judged and left on purpose remain", re-review after fixes). The hand-over step even specifies the exact report structure per reviewer. This matches the top anchor with checkpoints and error-recovery loops.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the under-50-line body is well organized into "Steps" and "After the hand-over" sections. Cross-references to sub-skills are one level deep, clearly signaled with links, and explicitly load-on-demand ("Read that skill when you reach the step, not before"), which is the essence of appropriate progressive disclosure for an orchestrator skill.

5 / 5

Total

19

/

20

Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, action-dense description that clearly communicates the end-to-end pipeline from issue to reviewed draft PR, with negligible fluff. Its main weakness is the absence of any explicit "Use when..." trigger guidance, which both caps completeness and leaves the when-to-invoke decision implicit.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to build, implement, or ship a change end to end — from an issue or spec to an opened, bot-reviewed draft PR."

Include natural user phrasings and synonyms ("take this issue to a PR", "ship this ticket", "implement and open a PR") to broaden trigger-term coverage.

State the invocation boundary explicitly (e.g., "Use when authorized to open a draft PR and reply to bot reviews on it") to further separate it from single-step PR-opening or code-review skills.

DimensionReasoningScore

Specificity

The description lists six concrete pipeline actions — "Implement, review, hunt invariants, QA in real projects, open the PR, act on the bot reviews, then hand over to a human" — with a concrete start state ("from the issue") and end state ("a reviewed draft PR"), matching the comprehensive-coverage anchor. It does not merely name a domain; each stage of the workflow is a specific action.

5 / 5

Completeness

The "what" is clearly and concretely answered (build a change end to end into a reviewed draft PR), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by the opening phrase. Per the rubric guideline, a missing explicit when clause caps completeness at 3; it is not a 4 because the when cannot be called even implicitly specific.

3 / 5

Trigger Term Quality

Natural terms like "build", "change", "issue", "draft PR", "review", and "QA" appear and would be said by a user needing this skill, giving good keyword coverage. A few natural phrases users might say are missing (e.g., "take this ticket to a PR", "ship this issue", "end to end" appears but no synonym variants), so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"Builds a change end to end, from the issue to a reviewed draft PR" carves a clear orchestration niche that subsumes rather than duplicates single-purpose skills (code review, QA, PR opening), giving mostly distinct triggers. It is not a 5 because phrases like "open the PR" and "review" have minor overlap risk with standalone PR-opening or code-review skills.

4 / 5

Total

16

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 missing, 13 suspicious

Warning

Total

13

/

16

Passed

Repository

storybookjs/storybook

Path

.agents/skills/build-it/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.