CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

spark-prairie-fire

星火燎原:从零起步、资源极少时,先评估客观条件,选定一个能站稳、能复用、能扩展的"根据地"(最小切入点),扎根后再逐步扩张,拒绝四处出击的流寇主义。当启动新项目、做 MVP / pilot、面对宏大目标不知从何下手、或做了很多零散事却没有积累时触发;项目已有稳固基础、只是修改现有系统时不触发。 English: Spark a prairie fire. When starting from almost nothing, assess the conditions, choose one base area (a minimal foothold that can hold, be reused, and expand), dig in, then grow step by step instead of scattering effort. Trigger for new projects, MVPs, pilots, daunting goals with no obvious first step, or busy work that accumulates nothing; skip when a solid base already exists or the task modifies an existing system.

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 concise, well-structured strategy skill with a clear sequenced workflow and explicit validation checkpoints. The two weakest points are actionability (blank template, no worked example) and progressive disclosure (a dead reference to a missing original-texts.md file).

Suggestions

Add one worked example that fills in the 输出模板 for a representative scenario (e.g., a from-scratch MVP) so the guidance covers a common case end-to-end and lifts actionability toward 5.

Provide the missing original-texts.md bundle file under ./references/ — or, if no source-text appendix is intended, remove the dead "原著依据:[original-texts.md]" link so navigation is not broken.

Make the failure-recovery path of the 流寇主义检查 explicit (e.g., 'if a checkbox fails, do not expand; return to 扎根 or adjust the base') to convert the implicit gating into a spelled-out feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence — no padding or explanations of concepts Claude already knows; the opening aphorism and metaphorical parentheticals are brief and load-bearing for a mnemonic strategy skill, so every section earns its place.

5 / 5

Actionability

Provides concrete, applicable guidance — a 5-step 操作规程, a four-element base-selection criterion, a 3-item 流寇主义检查 checklist, and a fill-in 输出模板 with specific fields; not 5 because the template is blank rather than a worked example covering a common case.

4 / 5

Workflow Clarity

Clear 5-step sequence with explicit validation: step 1 gates on conditions ("条件不足 → 先 investigation-first"), step 4 is a required pre-expansion checklist ("每次扩展前必须通过"), and step 5 enforces sequential gating ("前一步稳固后才走下一步"), matching the anchor for explicit validation steps plus checklists.

5 / 5

Progressive Disclosure

Well-organized into clear sections (用/不用, 操作规程, 输出模板, 纪律, 交接) with a clearly signaled one-level reference ("原著依据:[original-texts.md]"), but that referenced file does not exist in the bundle, so navigation is not clean — a minor gap rather than a fully navigable structure.

4 / 5

Total

18

/

20

Passed

Description

83%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 strong bilingual description that clearly states both capability and trigger conditions, including an explicit skip-when clause. The main weakness is overlap risk with closely related strategy-family skills on broad 'new project / daunting goal' triggers.

DimensionReasoningScore

Specificity

Lists several concrete actions — "评估客观条件", "选定…根据地…(最小切入点)", "扎根", "逐步扩张" — matching the 'several specific actions, minor gaps' anchor; not 5 because the actions are strategic/metaphorical rather than a comprehensive operational feature list.

4 / 5

Completeness

Explicitly answers both what (assess conditions, choose a reusable foothold, dig in, grow step by step) and when ("Trigger for new projects, MVPs…; skip when a solid base already exists or the task modifies an existing system") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings — "new projects, MVPs, pilots, daunting goals with no obvious first step, busy work that accumulates nothing" — giving good keyword coverage; not 5 because a few common synonyms are missing and there is no file-extension-style discriminator.

4 / 5

Distinctiveness Conflict Risk

Has a clear from-scratch base-building niche plus an explicit skip clause, but overlaps with sibling strategy skills named in the body (concentrate-forces, protracted-strategy, investigation-first) on 'new project / daunting goal' triggers, so it is mostly distinct with minor overlap risk rather than minimal.

4 / 5

Total

17

/

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

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository

HughYau/qiushi-skill

Path

skills/spark-prairie-fire/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.