CD dsh-session-projection
Use when creating, extending, or reviewing a DeepSeek Harness session projection, or migrating session-derived recovery state to one.
A skill for working with DeepSeek Harness session projections—meant for creating, extending, and migrating recovery state. Promises help with session data manipulation within the DeepSeek ecosystem.
One file with 1182 tokens inside. No critical or high-severity issues found, but broken references point to missing files—the skill references things that don't exist. Code quality scores 67, process score 35. Never ran on models, no sandbox testing. Claims to work across all platforms.
Install only if you specifically need these DeepSeek Harness operations and can handle missing dependencies yourself. For casual use, the overhead outweighs the benefit.
Keep recoverable session facts in Projection and expose them through their owning services.
As a process D 35/100 · Unfinished process — References files that are not bundled: ../../../packages/session/session-projection/README.md, ../../../docs/defensive-patterns/conversation-and-session.md
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../../../packages/session/session-projection/README.md - warning
missing-refreference to a missing file: ../../../docs/defensive-patterns/conversation-and-session.md
Process rating: all ten parameters 35/100
- 0Tools and files. 2 referenced file(s) missing: ../../../packages/session/session-projection/README.md, ../../../docs/defensive-patterns/conversation-and-session.md
- 0Result and completion. Does not say what the result is
- 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
- 30Running it twice. 2 mutating operations with no state check
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1182 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4Structure: 2 headings, hard to scan
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 133: enough signal without eating the budget
- +3Step-by-step instructions: 10 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.