CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review.

Quality

86%

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

73%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 a dense, repo-specific workflow guide with strong sequencing, explicit validation checkpoints, a pre-PR audit checklist, and concrete gh/go/git commands. Its main weakness is redundancy — the authorization formula and canonical-contract conditions are repeated across many sections — and its length as a single monolithic file with no bundle-level split.

Suggestions

State the authorization requirement ('obtain explicit authorization for the exact target, operation and credential/session; never probe ambient credentials') once in a dedicated section and cross-reference it from the workflow steps instead of repeating the full formula in at least four places.

Consolidate the PR-body honesty rules into the single 'PR body honesty' section and have Hard rules, the pre-PR checklist, and the anti-patterns table reference it, rather than restating the labels/count/failure rules in each place.

Replace the comment-only branch step with a concrete command sequence (e.g. the actual git checkout -b invocation with the branch-name regex) so every workflow step is executable.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and is mostly repo-specific rules, but it is noticeably repetitive: the authorization formula ('obtain explicit authorization for the exact remote destination, operation and credential/session') appears nearly verbatim in at least four sections, the canonical issue-creation contract conditions are restated in Hard rules 3-4, the scope table, and the verification protocol, and PR-body honesty rules are duplicated across Hard rule 8, PR workflow step 4, the PR body honesty section, the pre-PR checklist, and the anti-patterns table. Not 4: the repetition is more than minor trimming — stating each rule once and cross-referencing would cut a substantial fraction of the ~275 lines. Not 2: there is no basic-concept padding and most sections carry real, non-generic information.

3 / 5

Actionability

Concrete, copy-paste-ready commands are provided ('gh pr view <N> --repo "$TARGET" --json labels,closingIssuesReferences,additions,deletions,changedFiles', 'go build ./... ', 'go vet ./... ', 'go test ./internal/...', 'git diff --stat <base>...<head>') alongside exact regexes for branch names and PR titles and a section-by-section PR body template. Not 5: the branch step (PR workflow step 1) contains only comment placeholders with no actual command, and several directive rules (e.g. 'wait without mutation') are prose rather than executable steps. Not 3: the guidance is genuinely executable, not pseudocode, with only minor gaps.

4 / 5

Workflow Clarity

The PR workflow is clearly sequenced (branch → implement → local validation → draft body → chain diagram → post-publication reconciliation) with explicit validation checkpoints ('go build/vet/test' before drafting, pre-PR self-audit checklist with 15 tick-boxes, verification protocol steps 2-4 that cross-check API state), explicit error-recovery feedback loops (the standard honest-rewrite pattern, 'if different, request separate authorization before editing', pending-actions section), and a checklist for the complex process. Mutations (labels, protected labels) are explicitly gated with wait-without-mutation fallbacks, so no risky operation lacks validation.

5 / 5

Progressive Disclosure

The file is well-structured with clear section headers, and the References section points to one-level-deep source-of-truth files in the target repo (CONTRIBUTING.md, PR template, pr-check.yml, sibling SKILL.md files) rather than duplicating their contents — an effective disclosure pattern since the skill triggers only inside that repo. Not 5: no bundle files exist to split into, and the ~275-line monolith inlines substantial detail (full chained-PR strategy comparison, anti-pattern table, honesty pattern) that could live in referenced files; references point to repo paths rather than bundled files, so navigation depends on the target repo being present.

4 / 5

Total

16

/

20

Passed

Description

92%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 strong description: it explicitly states what the skill does and when to load it, uses natural trigger phrases, and is tightly scoped to one repository and contributor role so conflict risk is minimal. The only weakness is minor missing keyword variations such as spelling out 'pull request' or 'contribute'.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities ('Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage') and concrete actions ('opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review'), comprehensively covering the contribution flow. Not 4: coverage of the skill's scope is complete rather than having minor gaps.

5 / 5

Completeness

The 'what' is explicit (issue-first workflow, honest PR bodies, scope boundaries, chained-PR strategy, verification protocol, docstring coverage) and the 'when' is explicit with concrete trigger phrases ('Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, ...'). This matches the anchor for clearly answering both what AND when with concrete triggers.

5 / 5

Trigger Term Quality

Natural phrases users would say are present: 'opening an issue', 'drafting or editing a PR body', 'chained/stacked PRs', 'requesting review', 'external collaborator', plus the synonym pair 'chained/stacked'. Not 5: a few natural variations are missing (e.g. 'pull request' spelled out, 'contribute', 'code review'). Not 3: keyword coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a single named repository (Gentleman-Programming/gentle-ai) and a specific role (external collaborator, not maintainer), giving it a clear niche with distinct triggers and minimal conflict risk with other skills. It even names situations where it should NOT load, further reducing wrong-skill triggering.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Gentleman-Programming/gentle-ai

Path

skills/gentle-ai-collab-perfect/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.