CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qtpass-github

Opens and updates QtPass pull requests, rebases branches onto main, answers CodeRabbit, Copilot and human review comments, resolves review threads, reads CI failures and squash-merges under the main ruleset. Use when opening a PR, handling review comments, rebasing or force-pushing a branch, merging, checking CI status, or triaging a GitHub issue.

79

Quality

99%

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

100%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 exemplary SKILL.md body: lean, fully executable, and organized around four sequenced workflows with explicit verification and feedback loops. Detail is appropriately pushed to two well-signaled, one-level-deep reference files that exist in the bundle.

DimensionReasoningScore

Conciseness

The body is dense with executable commands, tables, and short policy bullets; every explanatory sentence carries repo-specific facts Claude cannot know (ruleset enforcement, required check names, approval dismissal, bot push behavior). There is no padding and no explanation of general git/GitHub concepts — e.g. the "--force-with-lease" note exists only to justify a destructive-operation rule — so anchor 5's "every token earns its place" fits better than anchor 4's "minor instances of over-explanation".

5 / 5

Actionability

Copy-paste-ready bash blocks throughout: "git commit -s -S -m \"Fix short description (#ISSUE)\"", "gh pr merge <PR> --squash --delete-branch", "gh run view <RUN_ID> --log-failed", plus concrete real check names ("Super-linter", "libFuzzer (ASan + UBSan)") and a failing-check→fix table. Fully executable guidance covering the common cases, matching anchor 5.

5 / 5

Workflow Clarity

Four workflows are clearly sequenced with explicit validation checkpoints ("Verify before moving on: 1. git log --show-signature -1 ... 2. gh pr checks <PR>") and explicit feedback loops ("repeat from step 1 until no unresolved threads remain and `gh pr checks <PR>` is green"; "push and re-run gh pr checks until every required check is green"). The destructive force-push path uses --force-with-lease with warnings, and merge has an ordered check-then-act list — anchor 5's validation, recovery loops, and checklists are all present.

5 / 5

Progressive Disclosure

The core workflows stay inline while detail is split one level deep into two real, verified bundle files, each with an explicit read-when signal: "commands.md: read when you need a gh command not shown above" and "troubleshooting.md: read when a merge is blocked, threads will not resolve, a bot pushed unsigned commits, or a push is rejected". Point-of-need pointers in the body ("see references/troubleshooting.md", "references/commands.md#fork-workflow") make navigation easy — anchor 5.

5 / 5

Total

20

/

20

Passed

Description

100%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 model description: concrete third-person action list, an explicit "Use when" trigger clause with natural vocabulary and synonyms, and a distinct repo-specific niche. No fluff, over-claims, or padding.

DimensionReasoningScore

Specificity

"Opens and updates QtPass pull requests, rebases branches onto main, answers CodeRabbit, Copilot and human review comments, resolves review threads, reads CI failures and squash-merges" lists six concrete actions spanning the full PR lifecycle, with no vague filler. Anchor 4 ("minor gaps in coverage") does not fit: the actions comprehensively cover branch-to-merge work, matching anchor 5.

5 / 5

Completeness

It explicitly answers both questions: the what is the six concrete actions, and the when is a literal "Use when ... or triaging a GitHub issue" clause with concrete trigger phrases. This matches the anchor-5 example structure exactly, so 4 ("'when' could be more explicit") does not apply.

5 / 5

Trigger Term Quality

"Use when opening a PR, handling review comments, rebasing or force-pushing a branch, merging, checking CI status, or triaging a GitHub issue" uses natural user phrasing, and the what-clause adds synonyms ("pull requests"/"PR", "rebases"/"force-pushing", "CI failures"/"CI status"). Coverage is comprehensive for this domain rather than merely "good with a few natural terms missing".

5 / 5

Distinctiveness Conflict Risk

The description is anchored to a clear niche: "QtPass pull requests", "CodeRabbit, Copilot", "the main ruleset" — repository- and workflow-specific triggers that no generic Git/GitHub skill would claim. Minimal conflict risk, matching anchor 5.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

IJHack/QtPass

Path

.opencode/skills/qtpass-github/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.