Five findings, all real.
**The chain prompts carried the target skill's own trigger.** `test-servers`
claims "a change needs a real server to exercise it", and both cases said
"against a real/live server" — so the model could load `testing`, then pick
`test-servers` from the ORIGINAL prompt, in that order, and score a hit that
would have survived deleting the pointer from `testing` entirely. Rewritten to
carry no server cue ("end to end"), and the measured rate fell from 100% / 67%
to 33% / 33%. That is the size of the artefact, and 33% is what the pointer
alone is worth. Both cases are now red against the 0.5 bar and stay that way:
`skills:eval` is not a gate, the number IS the finding, and lowering the bar to
turn the column green would discard the only signal this feature adds. Filed as
#2247 with the trap written down so a fix cannot re-measure the artefact.
**A deny list cannot bound a 14-turn run.** It only names tools known when it
was written, and this checkout configures an HTTP `mcp-docs` server in
`.mcp.json` while a contributor's own MCP servers and plugins add more. Now
`--allowedTools Read,Glob,Grep,Skill` (what the harness actually needs) plus
`--strict-mcp-config` with no `--mcp-config`, which drops every configured
server. The deny list stays alongside, since a deny is unconditional while an
allow list governs pre-approval. What remains outside all three is a
contributor's plugin tools; `--bare` would remove those and skills with them,
which would measure nothing — so that residual is stated rather than papered
over.
**The chain threshold compared inclusively.** "More often than not" is `> 0.5`,
and `>=` passes exactly half whenever RUNS is even — 2/4 would report a result
the criterion does not license. `passesThreshold` is now strict for chains and a
floor for first moves, and a strict bound of 1.0 is rejected up front rather
than failing every case while looking like a trigger problem.
**The doc's probe command still denied only four tools**, contradicting the
section's own promise that a probe and a scored case see the same policy.
Updated, with a note that it must move with the harness, plus a hand-off probe
form.
**The reporting had no automated coverage** — the one thing that could silently
merge the two measurements lived inside `main`. Extracted as `formatReport` and
tested: both headings, per-group thresholds, the two separate summaries, the
combined exit, and both single-kind selections.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ABdTnqyBodw6mHVVkGehqe
Signed-off-by: cliffhall <cliff@futurescale.com>
`skills:eval` ran every case with `--max-turns 1`, so it measured one
thing: whether a skill is the model's FIRST tool call. That is right for a
skill a user reaches directly, and it leaves a whole class unmeasured — a
skill reached from inside another skill's body. `testing` tells the model
that picking a fixture is `/test-servers` and that it has to load it, and
`test-servers` scores 5/5 while every one of those five cases asks for it
by name. A skill only ever reachable through a hand-off would score a
clean 100% with the hand-off silently never firing.
An eval case is now one of two shapes, and exactly one:
{ "prompt": "…", "expect": "test-servers" } first move, 1 turn
{ "prompt": "…", "chain": ["testing", "test-servers"] } hand-off, 14 turns
A chain must END with the skill whose file it lives in. The case exists to
measure whether THIS skill is reachable, so the file that goes red is the
one belonging to the skill that stopped being reached; anchoring on the
first link would file a `test-servers` measurement under `testing`, where
a `test-servers` description edit would never be seen. Links are checked
against the repo's model-invoked set, which is why both `verify:skills`
and `collectCases` now validate in a second pass — `test-servers` sorts
before `testing`, so a per-directory check would reject a live chain as
unknown purely because of where the alphabet put it.
Scoring is an ordered SUBSEQUENCE, not a prefix and not a contiguous run:
the model may load something before the chain starts and something
unrelated in between, and neither changes the claim that A led to B.
`collectSkillInvocations` therefore returns an ordered array rather than a
Set — a B, A, B run has to stay distinguishable from one that never
reached B from A.
The two rates are reported in separate columns and never summed. A
hand-off is a second-hop load over many turns; a first-move rate is the
model's opening move. `CHAIN_MAX_TURNS` (14) and `CHAIN_THRESHOLD` are
their own knobs for the same reason, and `CHAIN_THRESHOLD` defaults to
**0.5** rather than inheriting 0.8: see the measurement below.
Read-only containment no longer leans on `--max-turns 1`, which was doing
much of it by itself. The deny list gains the agentic and network tools —
`Task` in particular, whose subagent the flag does not reach.
Measured, `skills:eval -- test-servers`:
First move (1 turn) 7/7 at 100%, unchanged
Hand-off (14 turns) 67% and 33% at RUNS=3
So the hand-off is real and unreliable — which is the fact nothing could
observe before this change, and the reason 0.5 rather than 0.8 is the
default bar: at 0.8 both committed cases are red no matter how strongly
the first skill points at the second, and the column stops carrying
signal. A `["pr-flow", "test-servers"]` probe measured 0% and was dropped
rather than kept: `pr-flow` says nothing about fixtures, so the case had
no lever short of broadening a description onto another skill's ground.
Both findings are written up in `docs/skill-authoring.md`.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ABdTnqyBodw6mHVVkGehqe
Signed-off-by: cliffhall <cliff@futurescale.com>
Adds a multi-name filter to `npm run skills:eval` so a set of related
skills can be iterated together, and makes an unknown name a hard error
rather than an empty run — a typo would otherwise report a green 0/0
that reads exactly like a clean pass of the skill that was meant.
Re-aims two `local-dev` cases and one `test-servers` case that partially
overlapped `AGENTS.md`. Partial overlap oscillates across runs rather
than sitting at zero, so it reads as eval noise instead of a defect in
the case; `docs/skill-authoring.md` now records that failure mode and
the observed scores.
Widens the `test-servers` description to the "Use when …" shape and
points the `testing` skill at it, since anything needing a real server
to run against is a procedure `testing` does not carry. That growth
moves the skill listing from 2,921 to 3,144 of 4,000 characters, so the
figure recorded in AGENTS.md is updated to match.
Signed-off-by: cliffhall <cliff@futurescale.com>
`skills:eval` was at 38/46 with several skills measuring 0-33%. The low
scores were mostly bad eval cases rather than bad descriptions, for two
reasons that were nowhere written down:
- The harness runs each case with `--max-turns 1`, so the skill has to be
the model's FIRST tool call. A prompt asking "how does X work here", or
naming a concrete file, sends the model to Read/Grep first — a better
answer to the question, scored as a miss. Every 0% case was one of these.
- `AGENTS.md` is resident on every turn, so a prompt it already answers is
answered without any skill and the case can never pass.
Replace the cases that measured the wrong thing, expand every model-invoked
skill from 3 to 5 positives (negatives kept) so one flake cannot cross the
threshold, and reshape `local-dev`'s description to the action-first form.
Add `docs/skill-authoring.md` with the case shapes that fire, the ones that
cannot, and the probe-then-measure loop.
RUNS=5 npm run skills:eval: 63/63 at or above threshold, 60 at 100%,
all 18 negatives clean.
Closes#2202
Signed-off-by: cliffhall <cliff@futurescale.com>
`disable-model-invocation: true` does not merely make a skill prefer `/name` —
the model cannot invoke it at all, and its description is absent from the skill
listing. So "create a PR for #2163", which is how that work actually starts,
could never reach `pr-flow`. The original rationale ("procedures with side
effects we'd invoke by name anyway") conflates invoking a skill, which only
loads instructions, with performing the procedure it describes.
Flipped `pr-flow`, `pre-push-gate`, `board-ops` and `test-servers` to
model-invocable. `user-invocable` is an independent axis, so this is purely
additive — every `/name` still works. `issue-create`, `issue-triage` and
`release` stay deliberate.
`board-ops` is in the set because `pr-flow` and `issue-create` delegate their
card steps to it: a pointer from a model-invocable skill to a manual-only one is
a dead end for the model.
Costs weighed: the listing share goes 1,199 → 2,256 of 4,000, and a spurious
load costs ~250 characters where a missed one costs a wrong base branch or an
unsigned commit. The rules stay resident in AGENTS.md either way — this improves
the odds of getting the procedure too, it does not become the guarantee.
Eval cases committed for all four, measured at RUNS=3: pre-push-gate, board-ops
and test-servers 5/5; pr-flow 4/5, with "take it through to a pull request" at
100% and the Copilot-review case borderline. Three initial cases were replaced
rather than tuned green: their answers are resident in AGENTS.md, so the model
answering without the skill is correct behaviour, not a miss — the rule this
file already records about what makes a valid trigger case.
AGENTS.md's maintenance rule now says to default to `false` and explains why,
so the advice this change walks back does not get re-applied.
Signed-off-by: cliffhall <cliff@futurescale.com>