Repository navigation
Skill audit: fix inaccurate statements, fill gaps, add checks - #107
Merged
Merged
Conversation
Each statement of skills/fz/ was checked against the code and, where possible,
by running fz 2.0 (22 scenarios, plus a real fz-Modelica install).
Inaccurate statements fixed:
- SKILL.md fzd example: algorithm_options {"max_iterations": 50} for bfgs.py,
which reads only max_iter: the option was silently ignored (measured: 100
iterations instead of the requested number).
- code-wrapper.md: a runner exiting non-zero gives status "failed", not
"error".
- Reserved names (SKILL, reference, code-wrapper): log.txt, info.txt,
history.txt and .fz_hash are rewritten by fz; out.txt/err.txt are shared
with the captured stdout/stderr, so the last writer wins (measured both
orders), rather than "overwritten by stdout".
- Retries: on another calculator when there is one, else on the same, up to
FZ_MAX_RETRIES.
- reference.md: resuming after Ctrl+C into the same results_dir needs
cache://_ (cache://<results_dir> never hits there, as SKILL.md says).
- algorithm-wrapper.md: #title/#author are parsed but not displayed.
- Official repository names keep the code's case (fz-Modelica, fz-PSO), not
lowercase; "fz > 1.2" -> "fz >= 2.0".
Gaps filled: nsga2.py and montecarlo_uniform.R; fz-Model, fz-Algorithm and
fz-AlgorithmR templates; fzo's _output_error column; fzd's "algorithm" key;
python:// grep(group=, cast=); FZ_SSH_KEEPALIVE default (300).
tests/test_skill_static.py: every example algorithm is mentioned in the
skill; algorithm_options keys used in skill examples exist in the named
algorithm's #options header. Both fail on the previous skill.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RjXvVRjM6aMvKvvSFoxpZ6
yannrichet
pushed a commit
to Funz/fz.github.io
that referenced
this pull request
Nov 8, 2026
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RjXvVRjM6aMvKvvSFoxpZ6
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request
Description
This is an audit of the Agent Skill (
skills/fz/:SKILL.md,reference.md,code-wrapper.md,algorithm-wrapper.md) and of the plugin commands (commands/*.md) onmain(ec97161, version 2.0). Each statement was checked against the code (defaults, environment variables, CLI options, installer,python://helpers,output_expressionfunctions, MCP tools). Where possible it was also checked by running fz 2.0: 22 scenarios, plus a real install of the officialfz-Modelicawrapper from a local zip.The existing static tests only check that names are present. The inaccurate statements below passed them.
Related Issues
Relates to #106 (
fzdleaves an emptyiterNNN_<timestamp>directory per iteration — a code defect found during the audit, not addressed here)Type of Change
Changes Made
Inaccurate statements fixed
SKILL.md,fzdexamplealgorithm_options={"max_iterations": 50}forbfgs.pybfgs.pyreads onlymax_iter, so the option was silently ignored: 100 iterations ran instead of 50 (withmax_iter=2: 2 iterations)code-wrapper.md, runner"error"failed(Command failed with exit code N)SKILL.md,reference.md,code-wrapper.mdout.txtis "overwritten by the captured stdout"log.txt,info.txt,history.txt,.fz_hashare rewritten by fz;out.txt/err.txtare shared with the captured streams, and the last writer wins (both orders measured)FZ_MAX_RETRIESreference.mdcache://results_dirresults_dirthat never hits (asSKILL.mdalready says);cache://_is neededalgorithm-wrapper.md#title/#author"shown when listing algorithms"list_installed_algorithms()returns name, file, type, globalcode-wrapper.md,algorithm-wrapper.mdfz-<code>"(lowercase)"fz-Modelica,fz-Moret,fz-PSO)code-wrapper.mdGaps filled
nsga2.py(multi-objective, used with a list ofoutput_expression) andmontecarlo_uniform.R.fz-Model,fz-Algorithm,fz-AlgorithmR.fzo's_output_errorcolumn andfzd'salgorithmkey.python://grep(pattern, path, group=None, all=False, cast=True).FZ_SSH_KEEPALIVEdefault (300 s).Checks added to
tests/test_skill_static.pyexamples/algorithms/is mentioned in the skill.algorithm_optionskeys used in the skill's examples exist in the#optionsheader of the algorithm they name.Both fail on the previous skill (
nsga2.pymissing;max_iterationsnot declared bybfgs.py) and pass after the fixes.NEWS
One entry in the 2.0 "Claude Code plugin and Agent Skill" section, since the
2.0tag does not exist yet.Testing Performed
tests/test_skill_static.py,test_docs_consistency.py,test_readme_structure.py,test_docs_python_blocks.py: 23 passed.fzcnaming and renaming,fzoon a parent directory vs. a glob;sh://argument appending, statuses, reserved names;cache://resultsvs.cache://_;ValueErrorcases, callbacks, CLI exit code and the short form of--input_variables;fzdreturn keys, layout, function model and calculator auto-discovery;fz-Modelicainstall:Modelica.json, an executableModelica.shandlocalhost_Modelica.json, with--checkpassed.Not verified
skills/examples/*.md, Modelica + brent and OpenFOAM) were not run:omcand OpenFOAM are not available.ssh://,slurm://,funz://andfz-mcpwere checked in the code only.fz install model <name>downloads were blocked by the environment's proxy (HTTP 403 on GitHub archives); the install was tested from a local zip.Generated by Claude Code