CtrlK
BlogDocsLog inGet started
Tessl Logo

dev-workflow

The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.

62

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/dev-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strongly actionable, well-structured operational skill: every stage is backed by executable commands, URLs, and credentials, with testing and staging smoke tests serving as validation checkpoints. The only real costs are mild redundancy (enumerated smoke-test coverage, commit examples) and an implicit rather than explicit proceed-only-when-valid gate before PR creation.

DimensionReasoningScore

Conciseness

The body is dense, command-first, and assumes competence — no explanations of concepts Claude already knows. Minor trimmable padding exists: the 10-item enumeration of what smoke-test.sh validates and the six commit-format examples duplicate content readable from the referenced scripts. This places it at anchor 4 (efficient, minor instances that could be trimmed) rather than 5.

4 / 5

Actionability

Everything is copy-paste ready: concrete 'make' targets per stage, access URLs, a test-command table with scope and notes, staging credentials, mock-auth headers, and worked commit examples. Specific examples cover the common cases, matching the anchor fully.

5 / 5

Workflow Clarity

Four clearly sequenced stages (dev, testing, staging regression, PR) with validation checkpoints in the loop (test stage and 'Staging Regression (pre-PR validation)' with smoke test) plus a Common Issues error-recovery table. It falls short of 5 because there is no explicit 'only proceed when staging passes' feedback-loop statement; the destructive resets (dev-all-reset, db-reset) are optional utilities with warnings ('clears data volumes') rather than unvalidated steps in the core sequence.

4 / 5

Progressive Disclosure

No bundle files exist, so the skill is a single well-sectioned SKILL.md with clear headers (Trigger, Prerequisites, Stages, Commands, Common Issues) and one clearly signaled one-level reference ('See docs/13-parallel-workflow.md for full details'). Minor gaps: inline content like the smoke-test coverage list and commit-style examples could live in separate reference files, keeping it at anchor 4 rather than 5.

4 / 5

Total

17

/

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 solid, domain-scoped description with several concrete stage names and good natural keywords, but it lacks any explicit 'when to use' trigger clause, capping completeness. Adding a 'Use when...' sentence would lift it into the top band.

Suggestions

Append an explicit trigger clause, e.g. 'Use when starting local development, running tests or smoke tests, validating a change in staging, or creating a pull request for SkillHub.'

Spell out natural user phrases like 'pull request' and 'run tests' alongside abbreviations to broaden trigger-term coverage.

State the entry-point action concretely (e.g. 'make dev-all' one-command start) so the 'what' is operational rather than stage-naming.

DimensionReasoningScore

Specificity

The description lists several specific actions — "local dev, staging validation, testing, and PR creation" — matching the anchor for several specific actions with minor coverage gaps. It falls short of 5 because the actions are stage names rather than comprehensive concrete capabilities, and above 3 because it goes beyond naming just 1-2 actions.

4 / 5

Completeness

The "what" is clear ("complete development workflow... including local dev, staging validation, testing, and PR creation"), but there is no "Use when..." clause or equivalent explicit trigger guidance — the phrase "for SkillHub contributors" only weakly implies when, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Natural keywords like "local dev", "testing", "staging validation", and "PR creation" give good keyword coverage a user would plausibly say, matching anchor 4. It misses common variations such as "pull request", "build", or "run tests", keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Scoping to "SkillHub contributors" and its specific pipeline stages makes it mostly distinct with only minor overlap risk against generic dev-workflow or commit-message skills. It is not a 5 because terms like "testing" and "PR creation" are broadly shared with other development skills.

4 / 5

Total

15

/

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

referenced_paths_exist

Referenced path issues: 5 missing

Warning

Total

15

/

16

Passed

Repository
iflytek/skillhub
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.