new-feat

Use when starting a piece of feature or fix work in this repository — taking or opening its GitHub issue, cutting the branch (a worktree on the local bare repo, an in-place branch on the remote environment) and producing the implementation plan, including the wiki pages the work will make stale and its observability plan. Also the step for turning a tracker finding into a branch without publishing it.

Quality

86%

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

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.

The body is excellent: executable commands, a clearly sequenced workflow with an explicit attack-the-plan validation gate, and appropriate one-level-deep reference splitting. The only dimension with room to improve is conciseness, where a few elaborated plan bullets could be tightened.

Suggestions

Tighten the longest Step 2 bullets (observability plan, config-value citation) into shorter imperative clauses or a sub-list to reduce qualifying prose.

Avoid restating the 'report all four' list in both the opening and the Finish section — reference it once.

Dimension	Reasoning	Score
Conciseness	Dense and largely assumes Claude's competence with no padding about git/issues/worktrees, matching the 'efficient; minor instances that could be trimmed' anchor; not a 5 because a few Step 2 plan bullets (observability, config-value citation) run long and qualifying, and the four-things report is stated twice.	4 / 5
Actionability	Provides copy-paste-ready gh and git commands with full flag sets, a complete issue-body heredoc template, the pre-flight probe, and stacked-branch handling, covering the common cases per the top anchor.	5 / 5
Workflow Clarity	Clear ordered four-step sequence with explicit dependencies, a pre-flight gate before Step 0, and an explicit validation/feedback loop (stress-plan with every finding fixed or rejected in writing before implementation), plus checklists for the report and plan fields.	5 / 5
Progressive Disclosure	Well-sectioned overview (Steps 0–4, gates, Finish) with one real one-level-deep reference (references/skills-routing.md) that is clearly signaled in Step 4 and appropriately offloads skill-routing detail, matching the top anchor.	5 / 5
	Total	19 / 20 Passed

Description

80%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 is strong: it explicitly states both what the skill does and when to use it, with a clear distinct niche as the start-new-work entry point. Its weakest spot is trigger-term quality — the vocabulary is tilted toward internal jargon over the natural phrases a user would say.

Suggestions

Add a few natural user-facing trigger synonyms (e.g. 'new feature', 'start a fix', 'open an issue and branch for this') alongside the internal jargon.

Consider mentioning the issue-number / finding-ID input forms ('#412', 'osn-tracker#…') in the description, since they are the most common invocation patterns.

Dimension	Reasoning	Score
Specificity	Names several concrete actions (taking/opening the issue, cutting the branch, producing the plan including stale wiki pages and observability plan), matching the 'several specific actions; minor gaps' anchor; not a 5 because some actions remain process-abstract and the surface is repo-internal rather than self-contained.	4 / 5
Completeness	Explicitly answers both what (issue, branch, plan with stale-wiki and observability) and when ('Use when starting a piece of feature or fix work in this repository') with concrete trigger phrases, matching the top anchor; the 'when' is explicit and specific so it clears the 4 anchor.	5 / 5
Trigger Term Quality	Has a natural 'Use when starting a piece of feature or fix work' trigger and keywords like issue, branch, fix, but leans heavily on internal jargon (bare repo, worktree, tracker finding) and misses common user-facing synonyms, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Carves a clear niche as the work-startup orchestrator (issue→branch→plan→attacked plan) distinct from sibling skills like prep-pr, stress-plan, and rate-complexity, with minimal overlap risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: xchromo/osn
Path: .claude/skills/new-feat/SKILL.md
Commit: 5438649

Reviewed: ~11 hours 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.