SKILLEMALL.ai

CD dev-tasks

Manage Ralphy's `notes/` capture inbox (`ideas/`, `issues/`, `decisions/`) — the only dev tracker for Ralphy itself; there is no separate roadmap board. Two jobs: (1) CAPTURE — turn a tagged thought into a correctly-shaped, correctly-placed note (an idea, an issue, or a decision); (2) COLLISION-CHECK — before filing anything new, search the inbox for an existing entity that already covers it, and update that instead of spawning a duplicate. For the `notes/issues/` backlog itself — decomposing a brain-dump into issues, executing them, moving them across `done/`/`deprecated/` — defer to the `dev-issues` skill (filing/shaping) and `dev-loop` (execution); this skill keeps `ideas/` + `decisions/` capture plus the cross-inbox collision check. USE WHEN the user types `/dev-tasks`, says "log this idea", "file a note", "capture this", "record this decision", "what's in the inbox", "is there already a note/idea for X", "promote this note", or drops a half-formed idea mid-dev-session for safekeeping. See body for ALSO FIRE / DO NOT FIRE / HARD INVARIANTS.

alecs5am/ralphy Agent Skills author: alecs5am 1 file body ≈ 1 818 tokens Open the sourcegithub.com↗ analyzed 11 h ago

Manage Ralphy's notes/ capture inbox (ideas/, issues/, decisions/) — the only dev tracker for Ralphy itself; there is no separate roadmap board.

As a process D 46/100 · Unfinished process — References files that are not bundled: ../../../notes/README.md, ../dev-issues/SKILL.md

ProcedureOperations and projectstype and topics are labelled automatically from the skill text
JSON
Technical rating
C
80/100
safety, quality, tests
Safety 60%
100
Quality 40%
51
Run on models
none yet
Process rating
D
46/100
Unfinished process
References files that are not bundled: ../../../notes/README.md, ../dev-issues/SKILL.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: dev-tasks (alecs5am/ralphy)

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1060 chars, limit 1024
  • warning missing-ref reference to a missing file: ../../../notes/README.md
  • warning missing-ref reference to a missing file: ../dev-issues/SKILL.md
  • note frontmatter-key unknown frontmatter key "namespace"
  • note edit-residue the text marks something as outdated (lines 7, 43, 44, 55, 68, 85): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: ../../../notes/README.md, ../dev-issues/SKILL.md
  • 0Tools and files. 2 referenced file(s) missing: ../../../notes/README.md, ../dev-issues/SKILL.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 8 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 41 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1818 tokens
  • 100Progress reporting. Reports progress

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1060: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 41 items
  • +4Has examples (2 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.