CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

build-and-release

Fully automate building and releasing a coding task.

Quality

56%

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 ./plugin/skills/build-and-release/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 admirably lean and appropriately structured for a tiny orchestration skill, but its guidance is not executable: the core steps are unelaborated skill names and the workflow has no validation checkpoints before consequential merge/release operations. Adding concrete invocation details and readiness/failure checks would raise both weak dimensions.

Suggestions

Specify how to invoke the subagent and the 'build'/'release' skills concretely (e.g. the exact skill invocation or command, and what arguments $ARGUMENTS passes through).

Add a validation checkpoint before the merge step, e.g. 'Only merge once the build skill reports success and CI checks pass on the PR.'

Define what 'ready PR' means (approved, green CI, no conflicts) and include a recovery step for when build or release fails.

DimensionReasoningScore

Conciseness

The 11-line body contains zero padding and no explanations of concepts Claude already knows: a heading, a one-line purpose statement, a numbered 3-step list, and the task placeholder. Every token earns its place, matching the 'Lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

Two of the three steps are bare skill names ('build', 'release') with no invocation syntax, arguments, or expected behavior, and the merge step ('Merge the ready PR and continue from updated main') gives no command or criteria. This is high-level hints missing the specific steps to execute, matching anchor 2; it is above anchor 1 only because the sequence and named skills provide minimal concrete guidance.

2 / 5

Workflow Clarity

A rough sequence is present (build, merge, release) but the steps are poorly defined and validation is entirely absent: no criteria for what makes a PR 'ready', no check that the build passed before merging, and no failure handling before an outward-facing release. Merging and releasing are consequential operations, so the missing validation caps the score at 3, and the poorly defined steps place it at anchor 2.

2 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external file references (none exist in the bundle), yet is well organized with a heading, a purpose line, and a numbered list. Per the simple-skill guideline, this matches the top anchor: clear, appropriately split, easy to navigate.

5 / 5

Total

14

/

20

Passed

Description

36%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 short and names its domain, but it is too vague to score well: it states no concrete actions, includes no 'when to use' trigger guidance, and uses the unnatural phrase 'coding task'. It is only weakly distinguishable from generic deploy/CI skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to build and release a project, ship a change, or run build-then-release workflows.'

State 1-2 concrete actions, e.g. 'Runs the build skill, merges the ready PR into main, then runs the release skill via a subagent.'

Include natural synonyms such as 'deploy', 'ship', 'publish', or 'release pipeline' so the description matches the phrases users actually say.

DimensionReasoningScore

Specificity

The description names the domain ('building and releasing a coding task') but its only action verb is the generic 'Fully automate', with no concrete actions described. This matches the anchor 'Names the domain but actions are minimal or generic' ('Processes PDF files'), not score 3, which requires 1-2 concrete actions.

2 / 5

Completeness

There is no 'Use when...' clause or equivalent trigger guidance at all, and the 'what' is vague: 'Fully automate' states an intent without any concrete capability, and 'a coding task' is unclear (you build software, not a task). Per the guideline a missing 'when' caps completeness at 3, but the vague 'what' with no 'when' matches anchor 2 ('Has a vague what and no when').

2 / 5

Trigger Term Quality

'building' and 'releasing' are natural keywords users would say, but common variations and synonyms ('deploy', 'ship', 'publish', 'CI', 'version release') are missing, and 'coding task' is phrasing a user would not naturally say. This matches the anchor 'Some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'Building and releasing' names a specific niche, giving it some distinctiveness, but the generic 'fully automate a coding task' framing would overlap with deployment, CI/CD, and git workflow skills. This matches the anchor 'Somewhat specific but could still overlap with similar skills', not score 4 which requires mostly distinct triggers.

3 / 5

Total

10

/

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

thedotmack/claude-mem

Path

plugin/skills/build-and-release/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.