CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

github-gitlab

Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills-seed/github-gitlab/SKILL.md
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.

The body is an operationally dense, well-sequenced guide: executable gh/glab/git commands for both GitHub and GitLab, approval-gated writes, and a bundled CI watcher with explicit merge gates and re-validation after head changes. Its only weakness is mild verbosity in the account-selection prose and the watcher's status semantics.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational rules ("A TLS timeout, connection reset, rate limit, or GitHub server error is not evidence of logout") and never explains basics Claude already knows, but a few passages could be tightened — e.g. the repeated identity caveats in "Choose the account deliberately" and the multi-sentence behavioral spec of the watcher. Efficient with minor trim opportunities: anchor 4, not the every-token-earns-its-place of anchor 5.

4 / 5

Actionability

Commands are copy-paste ready with standard placeholders and cover the common cases for both platforms: "gh repo view OWNER/REPO --json name,description,url,defaultBranchRef", "gh pr create --repo OWNER/REPO --title \"...\" --body-file pr.md", "glab mr create --repo GROUP/PROJECT --title \"...\" --description-file mr.md", "node \"<skill dir>/scripts/watch-ci.mjs\" --repo OWNER/REPO --pr NUMBER --head REVIEWED_HEAD_SHA", and "gh pr merge NUMBER --repo OWNER/REPO --squash --match-head-commit REVIEWED_HEAD_SHA". Fully executable guidance matching the anchor-5 example standard.

5 / 5

Workflow Clarity

Sections follow the real lifecycle — choose account, login only on confirmed rejection, read-only inspection, checkout/edits, approval-gated writes, CI wait, head-guarded merge — with explicit validation checkpoints ("Run the repo's tests", "Capture the full head SHA... before review", "Re-read checks and review threads immediately before merging") and feedback loops ("After any push or head change, discard old success/review evidence and repeat"). Destructive writes are gated by approval and the atomic --match-head-commit guard, so the missing-validation cap does not apply.

5 / 5

Progressive Disclosure

The single bundle file (scripts/watch-ci.mjs, verified to exist and be substantive) is referenced one level deep with its full invocation and rationale ("Use the bundled helper instead of a bare gh pr checks --watch"), and the polling/retry internals are correctly delegated to the script rather than inlined. Six clearly headed sections make the ~137-line body easy to navigate, with no nested or buried references.

5 / 5

Total

19

/

20

Passed

Description

53%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 names a specific niche (GitHub/GitLab via resident gh/glab/git auth) in third person without fluff or over-claims, but the generic "Work with" verb enumerates no concrete capabilities, and there is no "Use when..." clause or collaboration vocabulary (PR/MR/issue/CI). It is serviceable but below the good-example standard on both completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions GitHub or GitLab, pull requests, merge requests, issues, or asks to clone, inspect, or edit a hosted repo."

Replace the generic "Work with" with 1-2 concrete capabilities, e.g. "view issues and PRs/MRs, clone repos, push branches, open PRs/MRs, and watch CI."

Include natural synonyms users actually say — "PR", "MR", "issues", "CI checks" — to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain and a concrete mechanism — "Work with GitHub and GitLab repositories through resident gh/glab/git auth on the agent computer" — but the only action verb is the generic "Work with"; no specific capabilities (view issues, create PRs, watch CI) are enumerated. It is more informative than anchor 2 ("Names the domain but actions are minimal or generic") thanks to the named toolchain, but does not list the several specific actions required for anchor 4.

3 / 5

Completeness

The "what" is clear (working with GitHub/GitLab repositories via resident gh/glab/git auth), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. Not a 2 because the "what" is specific rather than vague; not a 4 because the "when" is wholly absent rather than merely under-specified.

3 / 5

Trigger Term Quality

"GitHub" and "GitLab" are natural terms users say, and "gh/glab/git" names the tools, but the description omits common variations and synonyms entirely — no "pull request", "PR", "merge request", "MR", "issue", or "CI". That is more than the "a few natural terms missing" of anchor 4, while clearly better than anchor 2's one or two generic keywords.

3 / 5

Distinctiveness Conflict Risk

"GitHub and GitLab repositories through resident gh/glab/git auth" carves a clear niche distinct from unrelated skills, with only minor overlap risk against closely related git/version-control or code-review skills. Below anchor 5 because the absent "when" triggers and the broad word "repositories" leave some ambiguity versus generic git workflows.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

yc-software/qm

Path

skills-seed/github-gitlab/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.