CF sdd-dev-workflow
规范驱动开发工作流（SDD + Speckit + Claude Code）。用于复杂软件开发项目。⚠️ 必需环境变量: ZHIPU_API_KEY。可选: GITHUB_TOKEN, ANTHROPIC_API_KEY。当用户需要开发复杂应用、进行多迭代开发项目、使用 sessions_spawn 自动化开发时使用此 skill。
As a process F 43/100 · Will not run — References files that are not bundled: references/long-running-agent.md, references/best-practices.md, references/monitoring.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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 · 5
-
high Dangerous commands
cmd-install-from-urlreferences/dependency-installation.md:297Installs a package from an untrusted URL / archivepip install -i https://pypi.tuna.tsinghua.edu.cn/simple <package>
Medium and low: 4
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/dependency-installation.md:107Pipe-to-shell installer from a well-known host (still executes remote code)curl -LsSf https://astral.sh/uv/install.sh | sh
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostreferences/installation.md:176Pipe-to-shell installer from a well-known host (still executes remote code)curl -LsSf https://astral.sh/uv/install.sh | sh
-
low Dangerous commands
cmd-pipe-to-shell-known-hostreferences/dependency-installation.md:27Pipe-to-shell installer from a well-known host (still executes remote code) (documentation table row)| **UV** | 包管理器 | `curl -LsSf https://astral.sh/uv/install.sh \| sh` |
table -
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/check-environment.sh:80Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)check_fail "UV 未安装" "curl -LsSf https://astral.sh/uv/install.sh | sh"
code literal
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/long-running-agent.md - warning
missing-refreference to a missing file: references/best-practices.md - warning
missing-refreference to a missing file: references/monitoring.md
Process rating: all ten parameters 43/100
- 0Tools and files. 3 referenced file(s) missing: references/long-running-agent.md, references/best-practices.md, references/monitoring.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2247 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
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
- -242 emoji in the instructions: noise for the model
- -32 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 167: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (19 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.