information-verification-through-provocation

Use when verifying rumors or sensitive intelligence without direct confrontation. Involves selecting an emotionally reactive proxy, designing a calibrated provocation to trigger unguarded responses, and interpreting reactions to confirm or deny suspected information, as demonstrated by Prince Shangchen.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./kg/ontology/ontology-v1/skus/procedural/skill_101/SKILL.md

Quality

Content

71%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 a concise, well-organized single-purpose skill with a clear sequenced workflow and a verification section. Its main weakness is actionability: several steps remain abstract where concrete, copy-ready guidance or a second worked example would help.

Suggestions

Make step 3 ('Design the provocation') concrete with specific calibration tactics or a mini-template (trigger, intensity, expected tell) instead of 'Create a scenario where disrespect... is delivered'.

Add a second short worked example covering the denial/innocent case so interpreters can see both confirm and deny reactions in practice.

Tighten the Verification section so it adds checks rather than restating step 5, removing the minor redundancy.

Dimension	Reasoning	Score
Conciseness	Lean and well-sectioned with no padding of concepts Claude already knows; the only redundancy is the Verification section restating parts of step 5, which could be trimmed.	4 / 5
Actionability	A grounded worked example anchors the method, but steps like 'Design the provocation' and 'Create a scenario where disrespect... is delivered' stay high-level rather than giving concrete, executable guidance.	3 / 5
Workflow Clarity	A clear 5-step sequence with a Verification section providing checkpoints (so not capped at 3), though the checkpoints sit at the end rather than interleaved as feedback loops within the flow.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no bundle files needed, and organized into clear labeled sections, meeting the simple-skill exception for full marks.	5 / 5
	Total	16 / 20 Passed

Description

80%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 well-structured, third-person, and clearly answers both what the skill does and when to use it, with a distinctive niche. The main weakness is trigger-term coverage, which uses a few relevant phrases but lacks synonyms and the natural variations users might actually say.

Suggestions

Add synonym trigger phrases such as 'confirm a suspicion', 'test a leak', or 'probe for the truth indirectly' so the description matches more natural user requests.

Expand the interpretation action with one concrete cue (e.g. 'an anger-tinged disclosure confirms; confusion or dismissal denies') to lift specificity toward full coverage.

Include a concrete situational trigger example (e.g. 'Use when you suspect a hidden decision but cannot ask directly') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("selecting an emotionally reactive proxy", "designing a calibrated provocation", "interpreting reactions to confirm or deny"), but the interpretation step lacks detail, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both: "Use when verifying rumors or sensitive intelligence..." (when) and "Involves selecting... designing... interpreting..." (what), with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Contains some relevant natural phrases ("verifying rumors", "sensitive intelligence without direct confrontation") but misses common synonyms and variations a user might actually say.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche (provocation-based information verification) with distinctive triggers and minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: baojie/shiji-kb
Path: kg/ontology/ontology-v1/skus/procedural/skill_101/SKILL.md
Commit: 6b836e3

Reviewed: 12 days ago

Table of Contents

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.