CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-issue

Use when writing a GitHub issue in this repository — planned work, a bug, an epic and its children, a follow-up a review or retro turned up, or a needs:decision proposal. Covers which repository it goes to, the title, type and labels, a body someone can act on months later with nothing checked out, the faults agent-written issues fall into, and the command that files it. Invoked by new-feat, prep-pr, retro and stress-plan whenever they open an issue.

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A well-crafted procedural skill: fully executable commands, a clearly sequenced workflow with explicit pre-filing validation, and honest handling of failure modes (duplicates, no-network). Its weaknesses are mild — some repetition of the routing rule across steps and inline detail that could be moved to reference files.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with no explanation of concepts Claude already knows, but the tracker-vs-public routing rule is restated across Steps 1, 2, 4 and 6, and a few sentences are convoluted ('An issue filed so a pull request this session opens can close it needs no exception.'), leaving minor instances that could be trimmed rather than a fully lean every-token-earns-its-place text.

4 / 5

Actionability

Guidance is fully executable: copy-paste-ready commands for search, label listing, issue creation with complete flags, and Project board manipulation with jq filters, plus concrete title patterns, a body template, a named-faults table, and worked examples in references/examples.md covering the common cases.

5 / 5

Workflow Clarity

Steps 0 through 6 are clearly sequenced with an explicit six-item 'Before running it, check' checklist, a duplicate search before filing, and a no-network fallback path — explicit validation checkpoints match the top anchor, and the destructive/batch cap does not apply since validation is present and the operation is neither batch nor destructive.

5 / 5

Progressive Disclosure

The one bundle reference (references/examples.md) exists and is clearly signaled, and wiki links are one-level deep with the fact restated in the body; however, ~184 lines carry detail such as the gh project board command sequence and label decision rules that could sit in reference files, which is a minor organization gap rather than the ideal clear-overview-with-split-content structure.

4 / 5

Total

18

/

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: explicit 'Use when' triggers with concrete scenarios, a precise inventory of what the skill covers, third-person voice throughout, and clear scoping that distinguishes it from neighboring skills. The only weakness is modest synonym coverage for how users phrase issue creation.

DimensionReasoningScore

Specificity

The description enumerates concrete actions — 'which repository it goes to, the title, type and labels, a body someone can act on months later', 'the faults agent-written issues fall into', 'the command that files it' — covering the issue-writing task comprehensively with no notable gaps, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers 'when' with a leading 'Use when writing a GitHub issue in this repository' clause listing concrete trigger scenarios, and 'what' with 'Covers which repository it goes to, the title, type and labels... and the command that files it' — both explicit and concrete, matching the top anchor rather than the 'when could be more specific' level below.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'planned work', 'a bug', 'an epic and its children', 'a follow-up a review or retro turned up', and 'a needs:decision proposal' give good keyword coverage, but common synonyms such as 'open an issue', 'file an issue' or 'ticket' are absent, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It claims a clear niche — writing GitHub issues in this repository — with distinct enumerated triggers (planned work, bug, epic, follow-up, needs:decision) and named sibling-skill invokers (new-feat, prep-pr, retro, stress-plan), leaving minimal conflict risk even against the closely related PR-writing skill, which it never touches.

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

englishstreetventures/osn

Path

.claude/skills/write-issue/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.