CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-management

Manage GitHub Issues 2.0 relationships with gh CLI: parent issues, sub-issues, blocked-by, and blocking links.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/issue-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 instruction-only skill body: fully executable commands with zero concept padding, a distinct safe-workflow section with an explicit verification step, and clean single-file organization that needs no bundle references. The only gap is the absence of an error-recovery loop after verification, which keeps workflow clarity at 4 rather than 5.

DimensionReasoningScore

Conciseness

The body is lean and command-driven: every section is a copy-paste example or a non-obvious operational caveat (version check, --add-sub-issue move semantics, blocked-by/blocking duality). It explains nothing Claude already knows — anchor 5 ('lean and efficient; every token earns its place'). Not anchor 4 because there are no sections that could be trimmed without losing real information.

5 / 5

Actionability

Every instruction is an executable, copy-paste-ready gh command with concrete issue numbers, covering create/edit/add/remove for all four relationship types plus human-readable, grep-able, and JSON inspection modes. This matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases') and exceeds anchor 4, which tolerates minor gaps — the version-capability preflight check even guards executability.

5 / 5

Workflow Clarity

The 'Safe workflow' section gives a clear 4-step sequence including an explicit verification step ('Verify with gh issue view ... --json parent,subIssues,...'), satisfying the batch-operation validation requirement that would otherwise cap the score at 3. It falls short of anchor 5 because there is no feedback loop — no instruction for what to do when verification shows the link is wrong or the command fails.

4 / 5

Progressive Disclosure

This is a single-purpose skill with no bundle files (references/, scripts/, assets/ are absent) and no content that warrants external files; the ~147-line body is a well-organized reference with clearly headed sections (reference format, parent/sub-issues, blocked-by/blocking, inspection, safe workflow). Per the simple-skill guidance, well-organized sections with no need for external references score 5; navigation is trivial and nothing is buried.

5 / 5

Total

19

/

20

Passed

Description

66%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 specific, well-scoped description with strong domain vocabulary and low conflict risk, but it omits any 'Use when...' trigger guidance, which caps completeness at 3 per the rubric guidelines. Adding an explicit trigger clause and a few more natural user phrasings would lift it to the top tier.

Suggestions

Add an explicit trigger clause to the description, e.g. 'Use when creating, editing, inspecting, or removing links between GitHub issues, or when the user mentions parent issues, sub-issues, or blocked-by/blocking relationships.'

Include more natural user phrasings as trigger terms, such as 'link issues', 'issue dependencies', 'epic', or 'break down an issue into sub-tasks', to broaden keyword coverage beyond the flag names.

Replace or supplement the single generic verb 'Manage' with the concrete actions covered by the skill (create, edit, inspect, remove relationships) to strengthen the 'what' answer.

DimensionReasoningScore

Specificity

The description names the domain ('GitHub Issues 2.0 relationships with gh CLI') and enumerates four concrete relationship types ('parent issues, sub-issues, blocked-by, and blocking links'), but uses only one generic action verb ('Manage') rather than multiple specific actions like create/edit/remove. It matches anchor 4 ('lists several specific actions; minor gaps') better than anchor 5, which expects multiple distinct concrete action verbs with comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (manage parent/sub-issue/blocked-by/blocking relationships via gh CLI) but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance in the description, which the judging guidelines explicitly cap at 3. The 'Use this skill when creating, editing...' sentence exists only in the body, not in the description field, so per 'score only what is explicitly stated' it cannot count here.

3 / 5

Trigger Term Quality

Good natural keywords users would say: 'parent issues', 'sub-issues', 'blocked-by', 'blocking', 'GitHub Issues'. A few natural phrasings are missing — 'link issues', 'issue dependencies', 'epic', 'task breakdown' — so it falls short of anchor 5's 'comprehensive coverage including synonyms'. It is clearly above anchor 3 ('some relevant keywords but missing common variations') because the core relationship vocabulary is present.

4 / 5

Distinctiveness Conflict Risk

The Issues 2.0 relationship niche (parent/sub-issue/blocked-by/blocking links) is a distinct specialty with minimal overlap against generic issue-creation or gh-CLI skills; only 'gh CLI' and 'GitHub Issues' overlap broadly. Anchor 5 requires a clear niche with minimal conflict risk — the terms 'manage' and 'gh CLI' alone could pull in general issue-editing requests, so anchor 4 ('mostly distinct; minor overlap risk with closely related skills') is the best fit.

4 / 5

Total

15

/

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
remotion-dev/remotion
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.