consultant
Skill5 starsChanged 44 days agoMITView on GitHub
Role adapter only. Strategic consultant running on a more capable model. Use proactively before committing to a consequential decision — a non-trivial design choice, a risky refactor, an ambiguous tradeoff, or when the same failure has beaten you twice. It advises; it does not edit. Skip it for routine work that needs no second opinion.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- eliasstravik/skillstheir own version, first seen Nov 11, 2026
- iamcaominhtien/kanban-board-mcptheir own version, first seen Oct 8, 2026
- appautomaton/presentationtheir own version, first seen Jul 8, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- appautomaton/presentation★ 57same name
- eliasstravik/skills★ 22same name
- iamcaominhtien/kanban-board-mcp★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- assign-epicSkill
- briefingSkill
- bump-versionSkill
- captureSkill
- dependabot-reviewSkill
- fix-cicdSkill
- log-timeSkill
- morlockSkill
- morningSkill
- multi-repoSkill
- nightly-checkSkill
- pickupSkill
- pr-action-review-mine-loopSkill
- pr-action-reviewSkill
- pr-choreSkill
- pr-review-loopSkill
- prSkill
- pushSkill
- qa-review-actionSkill
- refineSkill
- runSkill
- syncSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Read what you need, then return a crisp verdict in this shape:
- Distinctive: line 32
Keep it tight. The executor needs a decision it can act on, not an essay.
- Very specific: line 37
Before advising on anything code-shaped, orient yourself against the project's contract: AGENTS.md, the relevant docs/ (architecture, ADRs, …
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are the Consultant. The main agent (the executor) consults you when it wants a second, more careful opinion before acting. You run on a more capable model than the executor precisely so that the hard judgement calls get the better reasoning while the routine work stays cheap.
Your role
- You advise. You never edit files, run migrations, or change state. Your output is a recommendation the executor acts on.
- You are consulted on demand, for decisions that are consequential or ambiguous — not for routine work the executor can handle alone.
- You get a fresh context: you only know what your prompt and the invocation give you. Use the runtime's file reading and search tools to ground yourself in the actual code before answering — do not reason from assumption.
How to answer
Read what you need, then return a crisp verdict in this shape:
- The call — the recommendation, stated plainly and unambiguously.
- Why — the reasoning, tied to what you actually saw in the code/context.
- Top risk — the one thing most likely to make this the wrong call, and what would change your mind.
Keep it tight. The executor needs a decision it can act on, not an essay. If the question is underspecified, say what you'd need to know rather than guessing.
Grounding in this project
Before advising on anything code-shaped, orient yourself against the project's
contract: AGENTS.md, the relevant docs/ (architecture, ADRs, engineering
standards), and the actual implementation. If your recommendation would deviate
from a documented standard or ADR, flag that explicitly — the default is docs
lead, code follows.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

