zuhair-01/claude-skills-and-systems/analysis-contract

Claude Code and agent skill by zuhair-01/claude-skills-and-systems

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

The universal evidence and output contract for every analysis, research, study, teardown, audit, investigation, evaluation, and learn output — E1/E2/E3 evidence labels, [VERIFIED]/[CITED]/[ASSUMED] claim tags, the standard output shape (executive summary to sources), the 16-point quality rubric gate (score before vault promotion), the vault promotion rule, and volatility tags. Use whenever ANY analytical output is about to be written, scored, or promoted into the Second Brain vault.

Install

npx vskill@latest install zuhair-01/claude-skills-and-systems/analysis-contract

SKILL.md

The same SKILL.md was published earlier as zuhair-01/claude-skills-and-systems/analysis-contract.

Analysis Contract — the one quality layer for all analytical output

Applies to every lane (see analysis-lane-router). Any tool, any engine — the contract is engine-independent.

1. Evidence labels (every finding, every claim)

  • E1 — we did/verified it ourselves this session (measured, ran, read the real file)
  • E2 — reliable external source, cited with URL + capture date
  • E3 — plausible but unverified; [ASSUMED] until verified
  • Fine-grained tags on load-bearing claims: [VERIFIED: source] / [CITED] / [ASSUMED]
  • Never fabricate; remembered-but-unconfirmed = [unverified]; vendor claims = vendor-claimed

2. Output shape (recipe form — fill it, don't negotiate with it)

text
# Title
> [tool] tag line + date
## Executive summary (5-7 bullets)
## Findings (each: labeled E1/E2/E3 + dated + cited)
## Conflicts / open questions (state limits honestly)
## What this means for the user (prioritized actions)
## Sources (URL — what it proved — capture date)

3. Quality gate — score before promotion

Score the output against the 16-point rubric (Upgrade_2026_09\23_Deep_Research_Methodology.md §8; 0-2 per point, pass ≥10/16). <10/16 = draft, not vault-worthy — redo or downgrade to draft status. Record the self-score in the output footer.

4. Promotion rule (vault hygiene)

Only rubric-passing, evidence-labeled outputs enter 30 - Resources/Research/ (or the matching PARA folder). Drafts go to _Drafts/. Tag volatility on every research note: volatile (re-verify before use, e.g. pricing/policies) / semi-stable (re-verify quarterly) / stable (methods, math, architecture).

5. After landing

State that vault-search --reindex is needed so the brain remembers its own research (the known forgetting gap — see plan Phase 3). Log the run (one line: lane, engine, cost/time, rubric score) so lane choice becomes empirical.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/zuhair-01/claude-skills-and-systems/analysis-contract/badge)](https://verified-skill.com/skills/zuhair-01/claude-skills-and-systems/analysis-contract)

Something wrong with this skill or its page? Tell us.