New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Blind Rediscovery

by mtarcure in mtarcure/claude-vibe-squad

Operational checklist + helper for blind-rediscovery fan-out work.

MITAuto-check passed

Install Blind Rediscovery

skills CLI
$ npx skills add mtarcure/claude-vibe-squad --skill blind-rediscovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mtarcure/claude-vibe-squad blind-rediscovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/chrono-vault/skills/blind-rediscovery .claude/skills/blind-rediscovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
blind-rediscovery
GitHub stars
164
Token cost
~1.6k tokens
SKILL.md length
739 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Operational checklist + helper for blind-rediscovery fan-out work.

  • Works in 4 steps: Flag in the synthesis dossier — that… → The voice's INDEPENDENT targets (those… → Score system-validation against the… → …
  • Running Stage 3 hypothesis exploration on a target with prior chrono work
  • SKILL.md covers When to use, When NOT to use, Directory layout and What the dispatcher already…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Blind Rediscovery is an agent skill from mtarcure/claude-vibe-squad. Operational checklist + helper for blind-rediscovery fan-out work. Splits per-target dossiers into blind/ (voice-readable, no prior-finding refs) and curated/ (operator-only, prior findings + comparisons). Use when running Stage 3 hypothesis exploration on a target with prior chrono work.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex /… The licence is MIT.

When your agent uses it

  • Running Stage 3 hypothesis exploration on a target with prior chrono work

Example prompts

  • “/blind-rediscovery”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Flag in the synthesis dossier — that voice's contaminated targets cannot count as independent rediscovery
  2. The voice's INDEPENDENT targets (those not in priors) still count
  3. Score system-validation against the clean independent targets only
  4. Patch the _blind/ dossier authoring for next pass; update this checklist if the leak path was novel

What it can do on your machine

Read from SKILL.md and the folder at commit 7bd69f8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Blind Rediscovery loads about 1.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 739 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mtarcure/claude-vibe-squad at commit 7bd69f8, republished under its MIT licence (© mtarcure). 739 words, ~1,600 tokens.

Download SKILL.mdSave it as .claude/skills/blind-rediscovery/SKILL.md (or your agent's skills folder).
name
blind-rediscovery
description
Operational checklist + helper for blind-rediscovery fan-out work. Splits per-target dossiers into _blind/ (voice-readable, no prior-finding refs) and _curated/ (operator-only, prior findings + comparisons). Use when running Stage 3 hypothesis exploration on a target with prior chrono work.
type
skill

Blind rediscovery — operational checklist

When chrono runs blind rediscovery (e.g. "does v1.3 reproduce findings from a prior daemon run?") the validation signal IS voice independence. If a fan-out voice reads a Stage N dossier that names prior findings by ID/class, the experiment is invalid.

This skill operationalizes the _blind/ vs _curated/ split codified in CLAUDE.md "Dossier authoring convention" so the discipline becomes a checklist, not just prose.

When to use

  • Running Stage 3 hypothesis exploration on a target with EXISTING saved findings
  • Validating a v1.3 system pass against legacy daemon work from a predecessor project
  • Any case where "did the voices arrive at this independently?" is the core question

When NOT to use

  • Resuming a known finding for PoC drafting (Stage 4) — voices need the prior work
  • New target with no prior chrono history — there's nothing to contaminate
  • Bulk-mechanical refactor / lint pass — no judgment, no voice independence to preserve

Directory layout

For a target with the slug <target>. The casing is load-bearing: dispatch_context_builder. enforce_blind_floor() keys the dispatch-level floor on exactly this path, and the maintainer's volume is case-insensitive, so a lowercase chrono/ here would resolve locally and fail on a case-sensitive filesystem.

$CHRONO_VAULT_ROOT/Chrono/dossiers/<target>/
├── _blind/                          # fan-out voices CAN read this
│   ├── stage-1-scope-<date>.md
│   ├── stage-2-codebase-map-<date>.md   # NO prior-finding refs
│   └── ...
├── _curated/                        # ONLY brain + operator read this
│   ├── prior-findings.md            # F1, F2, etc — the saved work
│   ├── stage-3-synthesis-<date>.md  # comparison-with-prior happens here
│   └── methodology-notes.md
├── raw-voices/                      # raw fan-out outputs (also voice-readable)
└── _resume.md                       # session-resume index, brain-readable

What the dispatcher already guarantees

Since 2026-08-17 the _blind/ directory is not only a convention — it is enforced. When a packet declares target: <target> and that dossier has a _blind/ directory, build_context forces memory_aperture: cold for every role whose specialist brief declares blind_discovery: true, regardless of what the packet asked for. The briefs under departments/*/specialists/ and shared/specialists/ are the roster; grep them for the key rather than trusting a list copied into prose. See shared/protocol.md § The blindness floor.

target: is free text and stays free text — the floor reads dossier slugs out of whatever the field contains (examplechain/<target>@0000aaaa, <target> / example-chain-node @ 1111bbbb, Target), so it fires on the live packet convention without the packet having to change vocabulary. A target: that names no blinded dossier leaves the aperture alone; it is never a dispatch error. Naming the dossier slug plainly is still the clearest thing to write.

That covers vault recall. It does not cover the two contamination paths below — dossier prose that names prior findings, and web search for prior art. Those remain the author's job, which is what the rest of this checklist is for. Set target: on every blind-rediscovery packet; the floor is target-scoped and has nothing to key on without it.

Show full SKILL.md (343 more words)Show less

Pre-fan-out checklist

Before assembling the fan-out brief, verify ALL of:

  • Every packet in the blind stage declares target: <target> so the dispatch-level floor applies

  • _blind/ exists; voice-readable dossiers live there

  • _curated/ exists; prior-findings + comparison docs live there

  • _blind/stage-N-*.md files contain NO references to: prior finding IDs (fnd_*), prior attack classes (e.g. "stale BRIDGE_PROVIDER_ROLE"), or prior PoC sketches

  • _blind/stage-N-*.md files DO contain: scope manifest, codebase map (architectural only), program rules, in-scope vuln class taxonomy

  • Brief explicitly tells voices to read ONLY _blind/ paths

  • Brief explicitly forbids reading _curated/ paths (use exact Do NOT read /path/to/_curated/ framing)

  • Brief forbids web search for prior art on the target (prior submissions on the target platform, GitHub issues, etc.)

Post-fan-out synthesis (where contamination is allowed)

After voices return their independent outputs, the synthesis stage IS allowed to read _curated/ for comparison. Synthesis dossier lives in _curated/, not _blind/. Synthesis includes:

  • Convergence table: which targets did N voices independently surface?
  • Comparison to prior findings: did voices rediscover F1 / F2 etc.?
  • Minority report: single-voice insights worth preserving
  • Contamination notes: any _blind/ content that accidentally hinted at priors

If contamination is discovered mid-pass

If a voice's output reveals it had access to prior-finding hints (the "GPT-5.5 explicit caveat" pattern from 2026-04-30 Dexalot Stage 3):

  1. Flag in the synthesis dossier — that voice's contaminated targets cannot count as independent rediscovery
  2. The voice's INDEPENDENT targets (those not in priors) still count
  3. Score system-validation against the clean independent targets only
  4. Patch the _blind/ dossier authoring for next pass; update this checklist if the leak path was novel

Authoring rule for new stage dossiers

Every new dossier in _blind/ should pass this self-check:

"If a voice reading this dossier had no other knowledge of the target, would they end up with the same priors as a voice that has access to my full prior-findings file?"

If yes — the dossier is contaminated. Move the prior-finding refs to _curated/.

Cross-references

  • CLAUDE.md "Dossier authoring convention — _blind/ vs _curated/" section
  • feedback_chrono_blind_rediscovery_methodology (auto-memory) — durable rule
  • docs/phase9-cleanup-2026-04-30.md — Dexalot Stage 3 contamination case study
  • plugins/chrono-vault/skills/fan-out/SKILL.md — when fan-out vs single-dispatch

© mtarcure, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/chrono-vault/skills/blind-rediscovery of mtarcure/claude-vibe-squad.

Open the folder on GitHubat commit 7bd69f8

Compare with similar skills

Blind Rediscovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Blind Rediscovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Blind Rediscovery this skillmtarcure/claude-vibe-squad164—~1.6kAutomated safety check: PassMIT
It Operationsdavila7/claude-code-templates32k1 repos~3.7kAutomated safety check: PassMIT
Operator Approval Loopaffaan-m/ECC276k—~3.3kAutomated safety check: PassMIT
Business Operations Skillsalirezarezvani/claude-skills28k—~2.3kAutomated safety check: PassMIT
Fan Operationsvivy-yi/xiaohongshu-skills478—~1kAutomated safety check: PassNone
Kubernetes Operatoralirezarezvani/claude-skills28k—~2.8kAutomated safety check: PassMIT

Similar skills

  • It Operations

    davila7/claude-code-templates

    Manages IT infrastructure, monitoring, incident response, and service reliability.

    32k GitHub starsUsed in 1 repo~3.7k tokens
    DevOps & CloudAuto-check passed

  • Operator Approval Loop

    affaan-m/ECC

    Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    276k GitHub stars~3.3k tokensUpdated 4 days ago
    Auto-check passed

  • Business Operations Skills

    alirezarezvani/claude-skills

    A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…

    28k GitHub stars~2.3k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed

  • Fan Operations

    vivy-yi/xiaohongshu-skills

    A skill your agent uses when growing Xiaohongshu following, engaging with audience, building community, responding to comments and DMs, or increasing follower retention and loyalty

    478 GitHub stars~1k tokensUpdated 8 mo ago
    Productivity & AutomationAuto-check passed

  • Kubernetes Operator

    alirezarezvani/claude-skills

    A skill your agent uses when building a Kubernetes Operator — custom controllers that reconcile CRD state.

    28k GitHub stars~2.8k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

  • MoviePilot Media Server Operations

    jxxghp/MoviePilot

    Inspects and operates Emby, Jellyfin, Plex and other media servers configured in MoviePilot through one helper script, without exposing stored credentials.

    12k GitHub stars~3.4k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from mtarcure/claude-vibe-squad

All 17 skills in this repo

  • Systematic Attacking

    mtarcure/claude-vibe-squad

    A skill your agent uses for ALL authorized offensive-security / bug-bounty work — the single method to find, chain, prove, dedup, and package the highest-value (High/Critical) findings across every…

    164 GitHub stars~3.6k tokensUpdated 18 days ago
    Auto-check passed

  • Chain Construct Smart Contract

    mtarcure/claude-vibe-squad

    A skill your agent uses when you have a confirmed on-chain vulnerability hypothesis and must demonstrate it with a passing proof-of-concept — author an attacker contract or crafted instruction…

    164 GitHub stars~1.5k tokensUpdated 18 days ago
    Auto-check passed

  • Compact Now

    mtarcure/claude-vibe-squad

    Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude…

    164 GitHub stars~1.6k tokensUpdated 18 days ago
    Auto-check passed

  • Agent Prompt Engineering

    mtarcure/claude-vibe-squad

    A skill your agent uses when building or revising the system prompt for a product agent and you need an eval-backed boundary, tool-use, grounding, and output contract.

    164 GitHub stars~872 tokensUpdated 18 days ago
    Auto-check: warnings

  • Defi Invariant Check

    mtarcure/claude-vibe-squad

    A skill your agent uses when the audit target is a DeFi protocol — AMM, lending market, yield vault, stablecoin, or perps — and you must author the economic properties generic campaigns miss, such…

    164 GitHub stars~2.5k tokensUpdated 18 days ago
    Auto-check passed

  • Dependency Cycle Audit

    mtarcure/claude-vibe-squad

    A skill your agent uses when module, package, or build dependencies may contain cycles, especially load-order failures, broad rebuilds, or a planned extraction: derive the real graph, compute…

    164 GitHub stars~1.5k tokensUpdated 18 days ago
    Auto-check passed

Questions about Blind Rediscovery

What does Blind Rediscovery do?

Operational checklist + helper for blind-rediscovery fan-out work. Blind Rediscovery is an agent skill from mtarcure/claude-vibe-squad. Operational checklist + helper for blind-rediscovery fan-out work.

When should I use Blind Rediscovery?

Blind Rediscovery fits situations like: running Stage 3 hypothesis exploration on a target with prior chrono work.

How do I install Blind Rediscovery in Claude Code?

Run `npx skills add mtarcure/claude-vibe-squad --skill blind-rediscovery -a claude-code`. Or copy the skill folder (plugins/chrono-vault/skills/blind-rediscovery in mtarcure/claude-vibe-squad) into .claude/skills/blind-rediscovery in your project. Claude Code loads it when a task matches its description.

How do I install Blind Rediscovery in Codex?

Run `npx skills add mtarcure/claude-vibe-squad --skill blind-rediscovery -a codex`. Or copy the skill folder (plugins/chrono-vault/skills/blind-rediscovery in mtarcure/claude-vibe-squad) into .agents/skills/blind-rediscovery in your project. Codex loads it when a task matches its description.

Can I use Blind Rediscovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mtarcure/claude-vibe-squad --skill blind-rediscovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/blind-rediscovery, .gemini/skills/blind-rediscovery, .github/skills/blind-rediscovery and .opencode/skills/blind-rediscovery in your project.

What does Blind Rediscovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Blind Rediscovery is instructions for the agent only.

Does Blind Rediscovery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Blind Rediscovery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Blind Rediscovery use?

Blind Rediscovery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Blind Rediscovery use?

About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Blind Rediscovery?

Skills that share tags, products or a category with Blind Rediscovery: It Operations (davila7/claude-code-templates, 32k stars), Operator Approval Loop (affaan-m/ECC, 276k stars), Business Operations Skills (alirezarezvani/claude-skills, 28k stars) and Fan Operations (vivy-yi/xiaohongshu-skills, 478 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Blind Rediscovery?

mtarcure (a GitHub user) maintains it in mtarcure/claude-vibe-squad, which has 164 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 21, 2026.

Source: mtarcure/claude-vibe-squad on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.