argument-construction-from-artifacts
Skill0 starsChanged 14 days agoMITView on GitHub
Build tool arguments from captured artifacts rather than from memory, so ids and paths are exact. Use when a tool needs an identifier that already exists in a capture, report or file
In this repository49 other files it gives its agents.
- audit-log-of-tool-callsSkill
- bounded-output-designSkill
- capability-negotiation-checkSkill
- changelog-and-versioningSkill
- concurrency-and-ordering-checkSkill
- context-window-managementSkill
- credential-isolationSkill
- data-retention-policySkill
- description-as-contractSkill
- destructive-action-confirmationSkill
- destructive-tool-gatingSkill
- deterministic-command-choicesSkill
- done-when-criteriaSkill
- error-shape-for-agentsSkill
- fixture-driven-transcript-testsSkill
- human-in-the-loop-escalationSkill
- idempotency-annotationSkill
- input-schema-strictnessSkill
- least-privilege-tool-grantsSkill
- lifecycle-test-initialize-then-toolsSkill
- local-vs-remote-boundarySkill
- one-procedure-per-skillSkill
- pagination-and-limit-disciplineSkill
- parallel-tool-call-safetySkill
- protocol-conformance-testSkill
- protocol-version-handshakeSkill
- publishing-a-pack-locallySkill
- rate-limit-respectSkill
- reference-canonicalisationSkill
- replay-transcript-for-regressionSkill
- restart-and-reload-semanticsSkill
- scope-guard-before-executionSkill
- search-then-fetch-patternSkill
- secrets-via-environmentSkill
- server-discovery-and-trustSkill
- signal-and-pitfall-sectionsSkill
- skill-frontmatter-contractSkill
- stdio-client-configSkill
- stdout-purity-checkSkill
- third-party-server-sandboxingSkill
- tool-call-budgetingSkill
- tool-call-error-pathsSkill
- tool-error-without-retry-stormSkill
- tools-list-schema-validationSkill
- tool-surface-minimisationSkill
- tool-verb-namingSkill
- transport-choiceSkill
- verify-tool-output-before-reportingSkill
- when-to-use-and-avoidSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 24
Check the returned record refers to the same identifier
- Distinctive: line 31
no argument was reconstructed from memory
- Distinctive: line 62
every exact-value argument is copied from a named artifact
≈ “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
Argument Construction From Artifacts
Build tool arguments from captured artifacts rather than from memory, so ids and paths are exact
Use when: a tool needs an identifier that already exists in a capture, report or file
Avoid when: the argument is a free-text query with no exactness requirement
Procedure
- Locate the artifact that holds the exact value
- Copy the value rather than retyping it
- Confirm the value's shape against the schema before the call
- Pass the smallest necessary set of arguments
- Check the returned record refers to the same identifier
- Record the source artifact beside the call for traceability
Signals
- the identifier in the call is byte-identical to the one in the artifact
- the result references the same object, not a similar one
- no argument was reconstructed from memory
- the source file path appears in the notes
Patterns
1. Copy not retype
slug taken from pack.json rather than the report2. Shape check
value matches ^[a-z0-9]+(-[a-z0-9]+)*$ before the call3. Traceability
argument source: results/catalog.md line 42Pitfalls
- Reconstructing a UUID or hash from memory and getting a near-miss
- Passing a display name where the tool expects a slug
- Losing the artifact reference so the call cannot be audited
Done when
- every exact-value argument is copied from a named artifact
- the result is confirmed to reference the same identifier
References
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.

