implement-story

Implements a GitHub user story from planning through PR creation, with research, codebase analysis, and structured commits.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/implement-story/SKILL.md

Quality

Content

85%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.

A strong, highly actionable process skill: phases, checkpoints, error-recovery loops, and repo-specific commands are all explicit and executable. Its main gaps are duplicated guidance that could be tightened and a monolithic single-file layout where a complex multi-phase workflow would benefit from one-level-deep reference files.

Suggestions

Deduplicate the 'don't build speculative config/sibling surface' guidance, which appears in both sections 1.3 and 3.2, stating it once in Phase 3.

Split stable reference material (the regeneration command table, PR title/format rules, and edge cases) into one-level-deep bundle files (e.g. references/regeneration.md, references/edge-cases.md) to reduce SKILL.md's inline weight.

Tighten section 3.2's overlapping principles (match patterns / design for siblings / unused config) into a single compact list.

Dimension	Reasoning	Score
Conciseness	The body is procedurally dense with almost no explanation of concepts Claude already knows, but guidance is duplicated (the 'do not ship unused config/sibling-story surface' advice appears in both 1.3 and 3.2, and approval checkpoints are restated), so minor trimming is possible.	4 / 5
Actionability	Concrete executable commands cover the common cases: git branch creation, gh issue search, a full regeneration task table, gh pr checks --watch, and explicit thresholds (under 70 chars, < 400 lines); the few open-ended steps (codebase research) are inherently flexible.	5 / 5
Workflow Clarity	Four phases are clearly sequenced with explicit validation checkpoints: user approval on the PR split, plan-mode approval before code, an AC coverage checklist, and a CI failure feedback loop (read logs, fix, push new commit, re-check).	5 / 5
Progressive Disclosure	Sections are well-organized, but ~230 lines are entirely inline with no bundle files; content that would fit separate references (regeneration command table, PR-format rules, edge cases) is inlined, and the only file pointers reference repo files rather than skill bundle files.	3 / 5
	Total	17 / 20 Passed

Description

58%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.

The description states a clear, specific capability chain (story -> plan -> PR) in third person without fluff, but it entirely lacks a 'when to use' trigger clause and natural trigger phrases. Adding an explicit 'Use when...' sentence with user-facing synonyms would raise completeness and trigger quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to implement a GitHub story issue, work an issue from planning to PR, or asks to pick up story #N.'

Include natural synonyms users would say ('implement issue', 'story issue', 'take this ticket to PR') to improve trigger term coverage.

Optionally name the deliverables more concretely (e.g. 'branch, commits, and PR(s) meeting acceptance criteria') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('planning through PR creation', 'research, codebase analysis, and structured commits'), but actions like 'planning' stay high-level and coverage is not comprehensive, matching anchor 4 rather than 5.	4 / 5
Completeness	The 'what' is clear (implement a user story into PRs) but there is no 'when' / 'Use when...' clause, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'GitHub user story' and 'PR' are natural keywords, but the description omits common variations users would say ('implement this issue', 'story issue') and includes no trigger phrases, matching anchor 3.	3 / 5
Distinctiveness Conflict Risk	'Implements a GitHub user story' carves a fairly distinct niche, with only minor overlap risk against generic coding or PR-creation skills; no distinct trigger phrases exist to justify a 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: stacklok/toolhive
Path: .claude/skills/implement-story/SKILL.md
Commit: 4c866b5

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.