envoy
Skill2 starsChanged 31 days agoApache-2.0View on GitHub
Turn a validated research record into a clear manuscript or response. Use for research communication, preserving claim-to-evidence links and explicit author decisions.
In this repository37 other files it gives its agents.
- canonSkill
- colorSkill
- formSkill
- graphicsSkill
- layoutSkill
- motionSkill
- pilotSkill
- systemsSkill
- typeSkill
- holdfastSkill
- aegisSkill
- assaySkill
- flightlineSkill
- gaugeSkill
- groundworkSkill
- gungnirSkill
- husbandrySkill
- load-bearingSkill
- pilotSkill
- plumbSkill
- stationkeepingSkill
- crucibleSkill
- forgeSkill
- ledgerSkill
- prospectSkill
- reckoningSkill
- forageSkill
- touchstoneSkill
- bearingsSkill
- bulwarkSkill
- keelSkill
- liverySkill
- lookoutSkill
- pilotSkill
- seaworthySkill
- trialsSkill
- wellspringSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 42
When this stage is fulfilled: checklist advance structure --run "$RUN".
- Distinctive: line 46
Write the argument, figures, and methods with enough detail to inspect or reproduce the work.
- Very specific: line 74
If an input or permission is missing, name the blocker and leave the relevant item pending.
- Very specific: line 80
After all required work and stage closures is recorded, use checklist done --run "$RUN".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
<!--
Copyright 2026 IamK77 — Licensed under the Apache License, Version 2.0.
See ./LICENSE and ./NOTICE · https://www.apache.org/licenses/LICENSE-2.0
-->envoy
Turn a validated research record into a clear manuscript or response. Use for research communication, preserving claim-to-evidence links and explicit author decisions.
Inputs
Claim set and limitations; experiment artifacts; target audience or venue; authorship and submission constraints.
Run record
Use checklist 0.5 or newer for this SOP. Reading or reloading the skill must not reset work. For a new task, run checklist init "${CLAUDE_SKILL_DIR}" --new --path "/absolute/project"; retain its returned ID as RUN. For existing work, use checklist resume "$RUN", then checklist show --run "$RUN". Outside Claude, replace the skill-directory variable with this directory’s actual path.
Commands below record work after it is done. Replace evidence placeholders with concise artifact locations and observations. Manual confirmations are not independent proof; a sensor pass covers only the command and inputs it observed. verify does not close a stage; advance checks that its required readings are fulfilled. Use report --run "$RUN" for the retained history.
Procedure
structure
Identify the reader’s question and organise the argument around supported claims. Separate contribution, method, evidence, and limitations before polishing prose.
Record these artifacts after doing the work:
- Outline connects the contribution to supported claims.
checklist check structure argument --run "$RUN" --evidence "<artifact and observation>" - Each factual claim has an attributable source or experiment artifact.
checklist check structure sources --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance structure --run "$RUN".
draft
Write the argument, figures, and methods with enough detail to inspect or reproduce the work. Verify citations and numeric consistency; never manufacture references, experiments, or author statements.
Record these artifacts after doing the work:
- Draft and figures faithfully represent the research record.
checklist check draft manuscript --run "$RUN" --evidence "<artifact and observation>" - Citations, numbers, methods, and limitations were cross-checked.
checklist check draft integrity --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance draft --run "$RUN".
review
Review against the actual target requirements and obtain author decisions on contentious claims. Prepare submission or response material; do not submit or contact others without explicit permission.
Record these artifacts after doing the work:
- Author review and unresolved issues are recorded.
checklist check review review --run "$RUN" --evidence "<artifact and observation>" - Requested manuscript or response package is complete for human review.
checklist check review package --run "$RUN" --evidence "<artifact and observation>"
When this stage is fulfilled: checklist advance review --run "$RUN".
Branches
For a rebuttal, answer the actual comment with evidence and mark new work clearly; no universal response deadline is assumed. If evidence is missing, narrow the claim or request the experiment.
If an input or permission is missing, name the blocker and leave the relevant item pending. A changed requirement may need a new run; an accepted checklist edit uses resume "$RUN" --refresh and requires fresh readings. To abandon work, use checklist reset --run "$RUN" --reason "<reason>"; history is retained.
Completion
A reviewable communication package. Submission, publication, and external correspondence require separate authorisation.
After all required work and stage closures is recorded, use checklist done --run "$RUN". This archives the result without deleting its history; it does not authorise any external action.
Reference shelf
Open the technique relevant to the current step. These notes provide concrete methods and examples, not additional phases; this entrypoint defines the run's completion conditions.
- Claim, citation, and authorship integrity
- Organise a manuscript around supported claims
- Prepare an attributable submission or response
- Build communication from the research record
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.

