iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/iterative-development/SKILL.mdQuality
Discovery
40%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 identifies a clear and distinctive niche around TDD iteration with Claude Code Stop hooks, which helps avoid conflicts with other skills. However, it lacks an explicit 'Use when...' clause, relies on somewhat technical jargon, and could benefit from listing more concrete actions and natural trigger terms that users would actually say.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to iterate on code using test-driven development, run tests automatically after each response, or set up a red-green-refactor loop.'
Include more natural trigger terms and variations such as 'test-driven development', 'red-green-refactor', 'auto-run tests', 'unit tests', 'test feedback loop'.
List additional concrete actions beyond the single workflow, e.g., 'Configures stop hooks, runs test suites after each code change, parses test failures, and re-prompts Claude with failure context.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TDD iteration loops) and mentions specific mechanisms (Claude Code Stop hooks, runs tests, feeds failures back), but doesn't list multiple distinct concrete actions—it's more of a single workflow description than a list of capabilities. | 2 / 3 |
Completeness | Describes what it does (TDD iteration with stop hooks, running tests, feeding failures back) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is only moderately clear, placing this at the low end. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'TDD', 'tests', 'failures', and 'Stop hooks', but misses common user variations like 'test-driven development', 'red-green-refactor', 'unit tests', 'test loop', or 'auto-test'. 'Claude Code Stop hooks' is fairly technical jargon. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'TDD iteration loops', 'Claude Code Stop hooks', and automatic test feedback creates a very specific niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with complete, executable scripts and clear workflow mechanics. Its main weakness is length — the philosophy boxes, use-case tables, and dual language variants make it verbose for a single SKILL.md without supporting bundle files. The core technical content (hook config + TDD loop script) is excellent and well-structured.
Suggestions
Move the Python variant, additional hooks (PreToolUse/SessionStart), and use-case guidance into separate bundle files referenced from the main SKILL.md to improve progressive disclosure and reduce token cost.
Remove the 'Core Philosophy' ASCII box — Claude doesn't need motivational framing; the behavior is already clear from the scripts and workflow diagram.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary verbosity — the ASCII box diagrams for 'Core Philosophy' add little value for Claude, the 'How It Actually Works' section partially repeats the concept intro, and the 'Good For / Not Good For' tables are things Claude can reason about. However, the code examples themselves are lean and the overall structure is reasonable. | 2 / 3 |
Actionability | Fully executable bash scripts, complete JSON configuration for hooks, and a Python variant are all copy-paste ready. The scripts include iteration tracking, safety limits, error output formatting, and proper exit codes — everything needed to implement this immediately. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced with the ASCII flow diagram showing the exact loop mechanics. The scripts include explicit validation checkpoints (test → lint → typecheck), error recovery via the exit code 2 feedback loop, a safety valve via MAX_ITERATIONS, and clear error classification distinguishing loopable vs non-loopable failures. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's quite long for a single file with no bundle files to offload detail into. The Python variant, additional hooks (PreToolUse, SessionStart), and the philosophy/use-case tables could be split into separate referenced files to keep the main SKILL.md leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
65efb33
- 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.