collaborative-research SKILL.md skillA
collaborative-research from yoavshmariahu/thinker is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yoavshmariahu/thinker/collaborative-research@git:20260928.9adafddPins git:20260928.9adafdd in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yoavshmariahu/thinker
- Path
.agents/skills/collaborative-research/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260928.9adafdd, committed Sep 28, 2026
- Size
- 5,041 bytes
- Repository stars
- 16
- License
- MIT
Conduct hypothesis-driven, collaborative, and iterative research on complex codebase performance, algorithmic retrieval, or benchmark regressions. Use when investigating non-trivial regressions, evaluating experiments against baselines, and synthesizing findings into reproducible research documentation.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Collaborative Iterative Research Skill
This skill guides agents through conducting structured, hypothesis-driven, and collaborative research with human engineers on complex codebase issues, benchmark regressions, or algorithmic optimizations.
---
## The 6-Phase Research Lifecycle
```
[Phase 1: Characterize] ──► [Phase 2: Diagnose] ──► [Phase 3: Align]
│
[Phase 6: Synthesize] ◄── [Phase 5: Validate] ◄── [Phase 4: Intervene]
```
### Phase 1: Problem Characterization & Baseline Anchoring
Never optimize or fix without quantitative baseline measurements.
1. **Gather Concrete Evidence**:
- Extract raw data from summary logs, execution traces, or transcripts.
- Separate wall time components: execution latency vs API streaming latency vs sleep/timeout intervals.
- Measure tool call density, tokens (input/output/cached), and error rates.
2. **Identify the Deviation**:
- Compare control (e.g. `nocache`) vs experiment (e.g. `cache`).
- Pinpoint specific anomalies (e.g., wall time increasing while tool calls decrease).
3. **Check Constraints**:
…Read the whole file at its exact version.
How to install
mdr add yoavshmariahu/thinker/collaborative-research@sha256:fff4951374260f4eThe line at the top of this page pins the label git:20260928.9adafdd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uvrakdyuxcpzjvie)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 28, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5041 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yoavshmariahu/thinker · 16 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uvrakdyuxcpzjvie GET https://markdownregistry.com/api/v1/resolve?ref=yoavshmariahu/thinker/collaborative-research GET https://markdownregistry.com/api/v1/blob/fff4951374260f4eb0eb12ab091fa97c445fff111820405c5e559e348d05645a
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.