AC sparc-methodology
SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use when: new feature implementation, complex implementations, architectural changes, system redesign, integration work, unclear requirements. Skip when: simple bug fixes, documentation updates, configuration changes, well-defined small tasks, routine maintenance.
The skill offers a five-step workflow for complex tasks: specification, pseudocode, architecture, refinement, completion. The idea is to force the AI to plan before coding instead of jumping straight to implementation.
Three files and two scripts in the package. Checks show no critical issues, code quality at 87/100, but process efficiency sits at 59 percent. Sandbox scripts stay within their directories. No medium-level findings.
Install it if you regularly hand the AI architectural work and tire of it diving into code immediately. Skip it for routine fixes and patches—the skill itself admits this upfront. Works across Claude, Cursor, and other listed platforms.
SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion.
As a process C 59/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: RA-Skills
How to improve
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 702 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 453: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (11 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 2 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/sparc-init.sh | ничего за пределами своей папки |
scripts/sparc-review.sh | ничего за пределами своей папки |
4 Oct 2026