outcome
Skill176 starsChanged 38 days agoMITView on GitHub
This skill should be used when the user asks to "run the outcome eval", "paired bare vs protocol", "which decisions did the protocol surface", "count what the AI asked or presented", "does /inquire surface what the request left out", or wants to see, from transcripts, which decisions reached the user as a question or something to recognize instead of having to be written into the opening prompt. Project-local contributor tooling.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- hiddenjobs/job-search-mcptheir own version, first seen Nov 1, 2026
- nomanAliShah786/claude-code-job-searchtheir own version, first seen Oct 11, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- hiddenjobs/job-search-mcp★ 28same name
- nomanAliShah786/claude-code-job-search★ 4same 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 repository27 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aitesis/AGENTS.mdAGENTS.md
- analogia/AGENTS.mdAGENTS.md
- anamnesis/AGENTS.mdAGENTS.md
- .claude/principles/AGENTS.mdAGENTS.md
- design/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- epharmoge/AGENTS.mdAGENTS.md
- epistemic-cooperative/AGENTS.mdAGENTS.md
- euporia/AGENTS.mdAGENTS.md
- heuresis/AGENTS.mdAGENTS.md
- horismos/AGENTS.mdAGENTS.md
- hyphegesis/AGENTS.mdAGENTS.md
- hypotyposis/AGENTS.mdAGENTS.md
- katalepsis/AGENTS.mdAGENTS.md
- lean/AGENTS.mdAGENTS.md
- merismos/AGENTS.mdAGENTS.md
- periagoge/AGENTS.mdAGENTS.md
- proplasma/AGENTS.mdAGENTS.md
- route/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- encapsulationSkill
- formal-reviewSkill
- realizeSkill
- rederiveSkill
- releaseSkill
- verifySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 80
Read references/runbook.md before the first run: the turn procedure, how to write the notes' items, authentication and isolation per …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Outcome Eval
Without a protocol, a person has to recall at length and write a long opening prompt. With one, they answer when asked, by recalling, or recognize what is put in front of them — and the items that come up this way can be ones nobody would have thought of at the start. This eval shows that one thing, from the transcript: the same request runs with and without the protocol, and each cell lists the decisions that reached the user through the AI.
The one measure
Per cell: the decision items that entered the conversation through the AI and that the user's opening request did not contain. Each is recorded with the verbatim span that raised it and how it reached the user:
asked— put as a question; the user answered by recalling.presented— shown as an option or default; the user recognized, picked or corrected it.
The number is the count of such items, per cell and per arm, shown under the opening request whose gaps they fill: each item is something the user would otherwise have had to write into that request. It is read from the transcript and the opening request alone — no hidden specification, no checklist, no grader of correctness. Identifying an item is a reading of the transcript, attributed to whoever wrote the cell's notes, not a mechanical extraction; the spans stay with it so anyone can check the reading.
What this eval measures, and what it does not
It shows how many decisions reached the user as a question or as something to recognize, rather than having to be written up front, and how many of them reached the user before any code existed — the only ones an answer could shape before the implementation. It does not show whether an answer then changed the code, whether the answers were right, whether a person felt less load, or anything about rework.
A result is an observation of one model on one day, and it changes as models change. A write-up
quotes every reportable cell of the runs it draws on, including cells where the arms did not
differ and cells where the bare arm raised more; picking cells turns an observation into a
showcase. It goes into
the pull request body or the commit message it informs, never onto a state surface — a README, an
AGENTS.md, this file — where nothing re-runs it. A surface may say that this eval exists and
what it counts; it does not say what it found. Records (results/) are gitignored for the same
reason.
Boundary with /realize
/realize judges whether a run follows a protocol's declared transitions. This skill reuses its
cases — scaffold, prompts, oracles, invocation lines and isolation — by path, and changes none of
them; a question about whether a gate fired belongs there.
Design
- Arms.
bareandprotocol. The protocol arm gets the plugin and/realize's invocation line, nothing else. A rule added to that arm alone would credit the protocol with what the harness added. - Dialogue. The user side is played mechanically by the variant's
oracle.md, up to the first turn that writes an implementation; a turn that neither implements nor hands anything back gets the case's go line once. The notes then close the cell. - Frozen case.
case.jsonholds the sha256 of every reused/realizefile and invocation line; every command that spends refuses when one has changed, since items read against a different request or oracle are a different case.
Runbook
S=.claude/skills/outcome/scripts/outcome.mjs
node $S plan --runner claude --model <model> --reps 2 --dry-run # argument check only
node $S plan --runner claude --model <model> --reps 2
node $S plan --runner codex --model gpt-6-luna --effort xhigh # borrows this machine's codex login
node $S setup <run> # codex: bare and protocol homes
node $S turn <run> <cell> --open # then --reply <file> | --go, as the oracle says
node $S note <run> <cell> # closes the cell; fill the items, then run again
node $S report <run> [<run> ...] [--out <dir>]
node $S teardown <run> # work trees and homes; records stayRead references/runbook.md before the first run: the turn procedure, how to write the notes'
items, authentication and isolation per runner, and why a Codex protocol cell writes code before
any answer can arrive.
Prerequisites and tests
Node 22+ and the runner's CLI (claude or codex) on PATH. The pure parts have a test that calls
no model:
node --test .claude/skills/outcome/scripts/lib.test.mjsDoes 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.

