CtrlK
BlogDocsLog inGet started
Tessl Logo

receive-handoff-grounding

接球前真相核验三问:claim → resolver → verdict (sourceTier T0/T1/T2 + actionFamily), 防止把传球者当无审视真相源(F167 Phase O 第一性原理)。 Use when: 即将调 hold_ball / register_pr_tracking / register_issue_tracking / merge / takeover / 改 owner / 任何 irreversible action / 基于 "operator signoff" 或 "你是 owner" 类 claim 行动之前。 Not for: 纯阅读 cross_post(无 actionFamily 后续);本 thread 日常 @mention 无副作用; implementation continuation(自检通过的下一步)。 Output: claim grounding verdict (verified/mismatch/insufficient) + 接球决策 (proceed / block / push back to source thread)。

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/receive-handoff-grounding/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 actionable and workflow-clear with strong validation structure, but it is over-long for a behavioral reflex and relies on referenced refs/ files that are absent, breaking progressive disclosure. Tightening redundancy and shipping the missing bundle files would raise the score.

Suggestions

Create the referenced bundle files (refs/resolver-catalog.md, refs/claim-schema.md, refs/dogfood-fixtures.md) or move their promised detail inline so navigation is functional.

Dedupe the repeated trigger/action rules across the trigger table, self-activation table, and self-check checklist to reduce length and redundancy.

Collapse the eight demo cases into a compact table or move them entirely to refs/dogfood-fixtures.md, keeping only one representative example inline.

DimensionReasoningScore

Conciseness

The body is dense and operational rather than padded with concept explanations, but at ~310 lines it restates the same rules across the trigger table, self-activation table, checklist, and demo section, so it could be tightened.

3 / 5

Actionability

Provides a concrete TypeScript WaitSourceRef schema, named resolvers/commands (gh api, git log --grep --author, feat_index.lookup), a push-back template, and a verdict×actionFamily action table; some resolvers remain abstract domain tools rather than copy-paste commands.

4 / 5

Workflow Clarity

Q1→Q2→Q3 is clearly sequenced with explicit validation checkpoints (verdict states, fail-closed, push-back feedback, a self-check checklist); the branching action-policy complexity keeps it just short of the top anchor.

4 / 5

Progressive Disclosure

Sections are well-organized and references are clearly signaled with descriptions, but the referenced bundle files (refs/resolver-catalog.md, refs/claim-schema.md, refs/dogfood-fixtures.md) do not exist, so navigation is non-functional and detail is promised but missing.

3 / 5

Total

14

/

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.

The description is specific, complete, and well-scoped: it states concrete actions, an explicit Use when/Not for trigger set, and a defined output. It is held back only by a few missing trigger synonyms and minor overlap with adjacent skills.

DimensionReasoningScore

Specificity

Lists several concrete actions (hold_ball, register_pr_tracking, register_issue_tracking, merge, takeover, owner change, irreversible) plus verdict and decision outputs, with only minor abstraction in the 'claim → resolver → verdict' wrapper.

4 / 5

Completeness

Explicitly answers what (接球前真相核验三问 with verdict states), when (Use when + Not for clauses with concrete triggers), and output (proceed/block/push back), matching the top anchor.

5 / 5

Trigger Term Quality

Good coverage of natural domain triggers including natural-language phrasings ('operator signoff', '你是 owner', '应该是你接'), though a few synonyms and variations are absent.

4 / 5

Distinctiveness Conflict Risk

Clear niche (pre-handoff claim grounding) with distinct tool/claim triggers and minimal conflict risk; only minor overlap with downstream merge-gate/worktree skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.