CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tapd-story-plan

迭代执行流水线开发计划阶段。基于 spec.md 调用 /speckit.plan 以测试驱动开发模式构建 开发计划、技术调研与数据模型,并在同一 subagent 内就地做文档级合规自检,产出 plan-report.md。 speckit 命令与报告模板详见 ../references/subagent-prompt-template.md §2.2。

Quality

77%

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 ./.agents/skills/tapd-story-pipeline/tapd-story-plan/SKILL.md
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.

This is a well-engineered orchestration sub-skill: lean, dense with operational specifics, and with explicit validation gates, retry loops, and rollback paths. The only notable gaps are its dependence on an external prompt template for full executability and reference hygiene (paths outside the bundle, one reference missing from the list).

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: it never re-explains known concepts, encodes checks as dense tables, and explicitly defers shared content ("均在 subagent-prompt-template.md §2.2 中定义,本子 skill 不重复"). Every section carries operational content, matching 'every token earns its place'.

5 / 5

Actionability

Guidance is highly concrete for an instruction-only skill: exact state transitions ('更新 meta.yaml.phase 为 researched'), exact retry limits ('同 attempt 内最多 3 个 round'), exact file paths and required rollback fields. It falls short of 5 only because the core executable artifact (the rendered SUBAGENT_PROMPT) is defined in an external template rather than reproducible from this file.

4 / 5

Workflow Clarity

The sequence is explicit with validation checkpoints and feedback loops: the 内容门禁 table defines pass criteria before consuming the verdict, needs_fix triggers round+1 retry, and spec_insufficient triggers a rollback re-entry with required attempt-patch fields. This matches 'explicit validation steps; feedback loops for error recovery; checklists'.

5 / 5

Progressive Disclosure

The body is a well-organized overview with one-level-deep, clearly signaled references and precise section anchors (§2.2, §1.3), and a dedicated 参考资料 list. Not 5: references point outside the skill bundle to ../references/ (unverifiable here), and shared-reentry-conventions.md is cited inline but omitted from the reference list.

4 / 5

Total

18

/

20

Passed

Description

58%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 communicates a specific, artifact-oriented pipeline stage with concrete actions and named outputs, and is appropriately concise. Its main weaknesses are the absence of an explicit 'Use when...' trigger clause (capping completeness) and missing natural trigger phrases that would aid discoverability and distinction from sibling pipeline skills.

Suggestions

Add an explicit trigger clause equivalent to 'Use when...', e.g. '当需求 phase 为 tech-clarised 且 spec.md 就绪时使用' / 'Use when a requirement enters the plan phase of the iteration pipeline', to raise completeness from 3.

Include natural trigger keywords and synonyms users would actually say (e.g. '开发计划', 'iteration planning', 'spec-to-plan', 'TDD 计划') so the skill is discoverable by phrase rather than only by pipeline state.

Mention the full output scope (e.g. contracts/, data-model.md) in the description to close the minor coverage gap in specificity.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "调用 /speckit.plan 以测试驱动开发模式构建开发计划、技术调研与数据模型", "就地做文档级合规自检,产出 plan-report.md" — with named artifacts. It stops short of score 5 because coverage of the stage's outputs is incomplete (e.g. contracts/ and error paths unmentioned), but exceeds score 3's '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is clear and multi-part (build plan/research/data-model, run compliance self-check, produce plan-report.md), but the 'when' is only weakly implied by the stage label "迭代执行流水线开发计划阶段" with no explicit 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant domain keywords are present ("spec.md", "开发计划", "技术调研", "合规自检", "plan-report.md") but the description lacks natural trigger phrasing and synonym variations a user would say. It fits 'some relevant keywords but missing common variations' rather than score 4's 'good keyword coverage with a few natural terms missing'.

3 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (pipeline plan phase, /speckit.plan, plan-report.md) that is mostly distinct, with only minor overlap risk against sibling pipeline-stage skills (specify/implement/review). Not 5 because the phase-oriented framing could collide with closely related speckit pipeline skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository

TencentBlueKing/bk-bcs

Path

.agents/skills/tapd-story-pipeline/tapd-story-plan/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.