CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-bundle-release

Bundle release workflow — checkout, prepare, pr, diff-check, audit, publish, sync.

58

Quality

68%

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 ./.skillshare/skills/1k-bundle-release/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured router skill: an executable shared detection script, explicit routing with aliases, a sequenced release flow with pre-publish verification steps, and clean one-level-deep disclosure into seven real, substantial reference guides. The main weaknesses are minor duplication between the Quick Reference table and Subcommand Routing, and the absence of an explicit failure/retry loop for the diff-check and audit gates.

DimensionReasoningScore

Conciseness

The body is efficient — a shared executable detection script, a routing table, and a compact flow diagram — with only minor trimmable redundancy: the Quick Reference table and Subcommand Routing section list the same seven subcommands with the same links, and the 'PRs target release/*, sync back to x via rebase' fact is stated in both the intro and Context. This matches 'efficient; minor instances of over-explanation that could be trimmed'; it is not 5 due to that duplication and not 3 because nothing is conceptually padded.

4 / 5

Actionability

The Release Branch Detection section gives a fully executable, copy-paste-ready bash script with an explicit failure path ('exit 1'), and routing rules are concrete with both names and numeric aliases. It sits at 'mostly executable; concrete code or commands with minor gaps' rather than 5 because the user-confirmation step and the Typical Release Flow are described at a directive level rather than as runnable commands, with the real detail deferred to the reference files.

4 / 5

Workflow Clarity

The Typical Release Flow sequences all seven steps, and validation checkpoints are present ('Before publishing — quick changeset review', 'Diff check passed — record release', audit recommended before publish, plus a y/n user confirmation after branch detection), so the destructive-operation cap does not apply. It matches 'clear sequence with most checkpoints present; minor validation gaps' — no explicit feedback loop (e.g., what to do when diff-check or audit fails) appears in the body, which keeps it below 5.

4 / 5

Progressive Disclosure

The body is a genuine overview: all seven subcommand guides live in one-level-deep references/rules/*.md files, every one of which exists with substantial content (64–354 lines), and each is clearly signaled twice (Quick Reference table with 'When to use' plus explicit Subcommand Routing). The reference files point back to SKILL.md rather than nesting deeper, matching the 'clear overview with well-signaled one-level-deep references' anchor exactly.

5 / 5

Total

17

/

20

Passed

Description

58%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 is concise and specific about what the skill does, listing all seven subcommands, but it entirely lacks a 'when to use' trigger clause, which both caps completeness and weakens trigger coverage. It is distinctive within its niche yet leans on subcommand jargon rather than natural user phrasing.

Suggestions

Add an explicit trigger clause, e.g., 'Use when working on bundle release features on release/* branches, publishing a bundle release, or syncing release changes back to x.'

Include natural user phrasings and synonyms alongside the subcommand names, such as 'release branch', 'version release', or 'rebase release changes', so the description matches how users would actually ask.

Briefly gloss what the key subcommands do (e.g., 'publish — record a release in RELEASES.json') so readers do not need to open the skill to understand the workflow stages.

DimensionReasoningScore

Specificity

The description names the domain ("Bundle release workflow") and lists seven concrete subcommands ("checkout, prepare, pr, diff-check, audit, publish, sync"), which matches the 'several specific actions; minor gaps' anchor. It falls short of 5 because the actions are bare subcommand names with no verb or object explaining what each does (e.g., 'prepare' what?), and it is well above 3 since far more than 1-2 actions are named.

4 / 5

Completeness

The 'what' is clear (manages a bundle release workflow with these seven steps), but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines. It is not 2 because the 'what' is specific rather than vague; it cannot be 4+ without an explicit 'when'.

3 / 5

Trigger Term Quality

Relevant keywords like "release", "publish", "checkout", and "audit" are present, but the list is subcommand jargon rather than natural user phrasing, and common variations/synonyms ("release branch", "version release", "deploy", "rebase") are missing — the 'some relevant keywords but missing common variations' anchor. It is not 4 because keyword coverage is not 'good with only a few missing'; several natural trigger phrases are absent.

3 / 5

Distinctiveness Conflict Risk

"Bundle release workflow" with a specific named subcommand pipeline carves out a clear niche with minimal conflict risk against unrelated skills, fitting 'mostly distinct; minor overlap risk'. It is not 5 because without any 'when' guidance, generic terms like 'publish' and 'pr' could overlap with general release/commit skills.

4 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 14 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 14 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.