CtrlK
BlogDocsLog inGet started
Tessl Logo

recipe-add-integration-tests

Add integration/E2E tests to existing codebase using Design Docs

56

Quality

63%

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 ./skills/recipe-add-integration-tests/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 content is a well-sequenced orchestration recipe with strong workflow clarity, explicit validation gates, and concrete subagent invocation details. Its main weaknesses are some unnecessary rationale prose that hurts conciseness and the absence of any bundle files to offload the dense gate logic.

Suggestions

Trim or remove explanatory rationale such as the "**Why Delegate**" paragraph and verbose gate prose; the procedural steps already convey the intent.

Extract the detailed response-gate tables and external-guide cross-references (e.g., HC-06, Review Resolution, Specialist Result Acceptance) into a references file so the SKILL.md body stays a lean overview.

Inline a one-line summary of the key external-guide behaviors (e.g., what Specialist Result Acceptance does) so the recipe remains actionable without forcing a context switch to another skill.

DimensionReasoningScore

Conciseness

The body is mostly dense procedural prose but includes unnecessary rationale such as "**Why Delegate**: Orchestrator's context is shared across all steps..." and verbose gate descriptions that could be trimmed, matching anchor 3 rather than the leaner anchor 4.

3 / 5

Actionability

Provides concrete, executable guidance — explicit subagent_type strings (e.g., "dev-workflows:acceptance-test-generator"), exact field mappings, and a copy-pasteable Step 4 prompt template — with minor gaps where external-guide sections (HC-06, Review Resolution, Specialist Result Acceptance) are referenced but not inlined, fitting anchor 4.

4 / 5

Workflow Clarity

Steps 1-7 are clearly sequenced with explicit response gates and validation checkpoints, plus feedback loops (Step 5 routes needs_revision back to Step 4; Step 6 routes stub_detected back to Step 3; verification_incomplete retries), matching anchor 5; the destructive/batch cap does not apply because validation steps are present.

5 / 5

Progressive Disclosure

The file has good section structure with clear headers and numbered steps and no broken references, but it is a single dense ~130-line file with no bundle files to offload detail; it is not a simple <50-line skill so the simple-skill exception does not apply, placing it at anchor 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

53%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 clear and reasonably specific about adding integration/E2E tests via Design Docs, but it omits an explicit "Use when..." trigger clause and natural synonyms that would improve discoverability. Adding trigger guidance would lift the completeness and trigger-term dimensions.

Suggestions

Append a "Use when..." clause naming concrete triggers (e.g., "Use when the user asks to add integration or end-to-end tests to an existing implementation that has Design Docs").

Broaden trigger terms with natural synonyms such as "end-to-end tests", "test coverage", and "automated tests" so users' phrasings match.

Optionally list 1-2 more concrete actions (e.g., "generate test skeletons, implement, and review integration tests") to raise specificity from a single action to multiple.

DimensionReasoningScore

Specificity

Quotes "Add integration/E2E tests to existing codebase using Design Docs" — names the domain and a single concrete action (add tests) plus the input source, but does not list several specific actions, matching anchor 3 rather than the multi-action anchor 4.

3 / 5

Completeness

Provides a clear "what" (add integration/E2E tests using Design Docs) but lacks any "Use when..." trigger clause; per the rubric a missing explicit trigger caps completeness at 3, and it does not rise to the both-what-and-when of anchor 4.

3 / 5

Trigger Term Quality

Includes "integration/E2E tests" and "Design Docs" as relevant keywords, but omits common synonyms users would say ("end-to-end tests", "test coverage", "automated tests"), fitting anchor 3 over the fuller coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The "using Design Docs" qualifier carves a clear niche, but the skill still overlaps somewhat with general test-generation skills, so it is "mostly distinct" (anchor 4) rather than the minimal-conflict anchor 5.

4 / 5

Total

13

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
shinpr/claude-code-workflows
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.