Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

tapd-iteration-init

迭代执行流水线启动器。分三个阶段执行：信息检查（验证 git 环境、获取迭代信息、解析迭代分支）→ 恢复检测（已有状态文件时判定恢复策略）→ 新流程初始化（创建分支、迭代目录和 iteration-state.json）。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tapd-iteration-runner/tapd-iteration-init/SKILL.md

Quality

Content

76%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 body is highly actionable and well-structured with executable dual-platform commands and a clear three-phase flow, but it silently suppresses remote-push failures and lacks a validation feedback loop on destructive operations. Bundling the referenced recovery.md would complete the progressive-disclosure picture.

Suggestions

Replace 'git push … || true' with an explicit success check and a retry/escalation path so remote-push failures surface instead of being silently swallowed.

Add a validation checkpoint after Phase 3 (e.g. verify branch exists on remote and iteration-state.json is valid JSON) before declaring the产出 guarantees met.

Bundle references/recovery.md (or inline its core mapping table) so the one-level reference the body points to actually resolves.

Dimension	Reasoning	Score
Conciseness	Lean and table/code-driven with no over-explanation of concepts Claude already knows; the per-command Bash + PowerShell duplication is justified for dual-platform support but could be slightly tightened, so it sits just below 5.	4 / 5
Actionability	Provides copy-paste-ready Bash and PowerShell commands for every operation, a concrete TAPD MCP call signature, regex branch-parsing, and a full iteration-state.json template — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	The three-phase sequence is clear with phase-1 failure-termination checkpoints, but destructive/remote operations lack a validate→fix→retry loop — 'git push -u origin "${VERSION}" 2>/dev/null \|\| true' silently swallows push failures — capping workflow clarity at 3 per the destructive-ops rule.	3 / 5
Progressive Disclosure	Well-sectioned into phases with recovery detail appropriately pushed to a one-level reference ('参见 references/recovery.md'); structure and signaling are good, though the referenced recovery.md is not actually bundled in references/, a minor organization gap keeping it below 5.	4 / 5
	Total	16 / 20 Passed

Description

63%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 specific and distinct, clearly enumerating the three-phase pipeline and its concrete actions, but it omits any 'when to use' trigger guidance, capping completeness and trigger-term quality. Adding a 'Use when…' clause with natural user phrasing would lift the weaker dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when starting a new TAPD iteration, initializing an iteration branch, or resuming an in-progress iteration.'

Include natural synonyms/users' phrasing ('启动迭代', '新建迭代', '继续迭代') so the description surfaces on real user requests.

Briefly state the entry condition (first sub-skill of the iteration pipeline) to sharpen the 'when' alongside the existing 'what'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the three phases — '验证 git 环境、获取迭代信息、解析迭代分支', '判定恢复策略', '创建分支、迭代目录和 iteration-state.json' — giving comprehensive coverage of what the launcher does.	5 / 5
Completeness	Clearly answers 'what' (three sequential phases with concrete sub-actions) but never states 'when' Claude should use it — no explicit trigger guidance, so completeness is capped at 3 per the missing-'Use when' rule.	3 / 5
Trigger Term Quality	Contains relevant domain keywords ('迭代', '流水线', '启动') but lacks a 'Use when…' trigger phrase and common synonyms/variations a user would naturally say; not below 3 since several real keywords are present, not 4 because natural trigger phrasing is absent.	3 / 5
Distinctiveness Conflict Risk	Targets a specific TAPD iteration-init niche ('迭代执行流水线启动器') with distinct triggers; mostly distinct with only minor overlap risk against sibling sub-skills like tapd-iteration-analysis.	4 / 5
	Total	15 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: TencentBlueKing/bk-bcs
Path: .agents/skills/tapd-iteration-runner/tapd-iteration-init/SKILL.md
Revision: 259aff2

Reviewed: 30 days ago

Discovery Implementation Validation

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.

tapd-iteration-init

Table of Contents

Is this your skill?