paker-it/devcon-hack-coach
Coaches you through scoping, shipping, and pitching a 24-hour hackathon project at AI Native DevCon (Tessl, London, 1–2 June 2026). Spec-first, track-aware, demo-obsessed. Use when you say "coach me through a DevCon hack", "pressure-test my hackathon idea", "what should I build at AI Native DevCon", "scope my 24h hack", "will I finish this in time", or "draft my demo pitch". Refuses to let you write code before a one-page spec exists.
100
100%
Does it follow best practices?
Impact
100%
1.69xAverage score across 5 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted description that clearly defines a narrow niche (hackathon coaching for a specific event), lists concrete actions, and provides explicit trigger phrases. The only minor issue is the use of second person ('you') in several places ('Coaches you', 'Refuses to let you'), which per the rubric guidelines should be penalized, but the specificity and completeness are otherwise excellent.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: scoping, shipping, pitching a hackathon project, pressure-testing ideas, drafting demo pitches, enforcing spec-first workflow. The phrase 'Refuses to let you write code before a one-page spec exists' is a distinctive behavioral detail. | 3 / 3 |
Completeness | Clearly answers both 'what' (coaches through scoping, shipping, pitching a 24-hour hackathon project) and 'when' (explicit 'Use when you say...' clause with six specific trigger phrases). Both dimensions are well-covered. | 3 / 3 |
Trigger Term Quality | Includes highly natural trigger phrases users would actually say: 'coach me through a DevCon hack', 'pressure-test my hackathon idea', 'scope my 24h hack', 'will I finish this in time', 'draft my demo pitch'. Good coverage of variations around hackathon coaching needs. | 3 / 3 |
Distinctiveness Conflict Risk | Extremely niche: specific to AI Native DevCon (Tessl, London, 1–2 June 2026), 24-hour hackathon context, spec-first methodology. Very unlikely to conflict with any other skill due to the highly specific event and workflow focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted coaching skill. It's lean, opinionated, and highly structured with clear phase gates, concrete deliverables at each step, and strong anti-pattern guardrails. The progressive disclosure is textbook — overview in the main file with phase-appropriate references loaded on demand. The voice examples and anti-patterns give Claude precise behavioral anchors without over-explaining.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No padding, no explaining what hackathons are or how LLMs work. The voice examples are tight and functional. The anti-patterns list is lean and each entry is actionable. The skill assumes Claude's intelligence throughout. | 3 / 3 |
Actionability | Extremely concrete: exact questions to ask per turn, exact spec fields to fill, exact checkpoint hours with deliverables, exact pitch structure with word limits, exact judge questions. This is an instruction-only skill where code is explicitly out of scope, and the guidance is fully specific and executable. | 3 / 3 |
Workflow Clarity | Four phases are clearly sequenced with explicit exit gates that define when to proceed and when to loop back. Phase 3 includes a checkpoint table with hours and concrete deliverables. The 'never skip ahead' instruction and loop-back conditions (e.g., 'go back to Phase 2 and cut') provide clear feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | The main skill is a clear overview with well-signaled one-level-deep references (tracks, spec template, pitch template, worked examples). The instruction to 'load a reference only when its phase starts' is excellent progressive disclosure. References are clearly mapped to phases. | 3 / 3 |
Total | 12 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents