BC plandeck
A live visual Kanban board and continuity layer for long-running agentic tasks. Nobody wants to read a markdown plan or stare at raw HTML while an agent grinds for an hour, so Plandeck turns the plan into a board that organizes itself. Use it when a task is multi-step, long-running, or needs visual planning. Break the work into cards, declare which card depends on which, and Plandeck computes the critical path, auto-promotes cards to Ready as their dependencies clear, rolls up story-point estimates into an honest percent complete, and names the one next action. Plans, observed transitions, and last-known-good snapshots stay as plain files on disk, so they survive /clear and context resets. After a reset, run plandeck next to recover the single next move and its recent history. If the plan stops parsing, run plandeck doctor before using git. Renders a live board in the browser over SSE. Triggers on plan a project, break down a task, kanban board, task board, visual plan, long-running agent, agentic task, track dependencies, critical path, story-point estimates, what is next, mission journal, recover plan, plandeck.
A live visual Kanban board and continuity layer for long-running agentic tasks.
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 34. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1131 chars, limit 1024
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3852 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1131: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -34 of 5 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 13 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.